Average Precision Rate Research Articles

Automatic thresholding method for high-throughput digital polymerase chain reaction fluorescence images with uneven illumination

The demand for nucleic acid detection is increasing worldwide as people are impacted by infectious diseases. Digital polymerase chain reaction (dPCR), which is a revolutionized nucleic acid absolute quantitative analysis technology, plays a significant role in the detection of genetic material. However, the traditional threshold-based methods fail to obtain high-accuracy segmentation results and real-time performance from dPCR fluorescence images with uneven illumination. Therefore, we proposed a robust two-stage automatic thresholding method to deal with dPCR fluorescence images. This method adopts the background subtraction method and the improved Otsu method to extract reaction chambers of dPCR images in two stages. Especially for the second stage, the peak-weaken method based on the improved Otsu method greatly improves the real-time segmentation of uneven illumination regions. Our method significantly improves the accuracy and processing speed of the dPCR image segmentation compared to several mainstream methods. This method could effectively segment the reaction chambers of dPCR images in complex environments. The average precision rate is 99.71%, the execution time is 0.139 s. Experimental results demonstrate that our proposed strategy has superior segmentation performance for high-throughput dPCR fluorescence images with uneven illumination.

Analysis and Prediction of Influencing Factors of College Student Achievement Based on Machine Learning.

To effectively improve students’ performance and help educators monitor students’ learning situations, many colleges are committed to establishing systems that explore the influencing factors and predict student academic performance. However, because different colleges have different situations, the previous research results may not be applicable to ordinary Chinese colleges. This paper has two main objectives: to analyze the fluctuation of Chinese ordinary college student academic performance and to establish systems to predict performance. First, according to previous research results and the current situation of Chinese college students, a questionnaire was designed to collect data. Second, the chi-square test was used to analyze the contents of the questionnaire and identify the main features. Third, taking the main features as input, four classification prediction models are established by machine learning. Some traits of the students who did not pass all the examinations were also discovered. It might help student counselors and educators to take targeted measures. The experiment shows that the support vector machine classifier (SVC) model has the best and most stable effect. The average recall rate, precision rate, and accuracy rate reached 82.83%, 86.18%, and 80.96%, respectively.

Automatic surface crack detection using segmentation-based deep-learning approach

The detection of surface cracks or defects in roads, sewage pipes, pavements, shield tunnels lining, etc. has become a promising area of research creating a significant impact on various application domains. Maintenance and monitoring of the manufactured and natural structures are crucial for their correct functioning and integrity. An effective way to predict structural degradation and deterioration is by detecting crack formation, which defines bad health for any artificial or natural structure. Deep learning-based techniques are prominent in accurately identifying the cracks as opposed to the conventional machine learning techniques, which require large processing time and involves handcrafted features. A deep learning-based architecture for automatically detecting and segmenting the cracks in concrete based material surface is presented in the paper. The training and testing results are demonstrated on a newly created dataset consisting of 3000 images of surface cracks. We have manually annotated the cracks present in each image by drawing a bounding box and segmented mask around them. The testing results are evaluated on parameters such as crack detection accuracy, mean average precision rate (mAP), and crack detection speed. To overcome the data collection and labeling barriers, a part of the dataset is made publicly available for research purposes. The training speed and the convergence rate of the proposed algorithm are optimized by using the concept of transfer learning through freezing and unfreezing certain layers of the network. Additionally, the choice of appropriate hyperparameters for improving the model accuracy is discussed in the article. The performance of the model is evaluated against the ground truth labels generated. The AP is reported 74.156% and 93.445% at IoU (Intersection over union) threshold of 0.7 and 0.5 respectively for crack segmentation.

MeQryEP: A Texture Based Descriptor for Biomedical Image Retrieval.

Image texture analysis is a dynamic area of research in computer vision and image processing, with applications ranging from medical image analysis to image segmentation to content-based image retrieval and beyond. “Quinary encoding on mesh patterns (MeQryEP)” is a new approach to extracting texture features for indexing and retrieval of biomedical images, which is implemented in this work. An extension of the previous study, this research investigates the use of local quinary patterns (LQP) on mesh patterns in three different orientations. To encode the gray scale relationship between the central pixel and its surrounding neighbors in a two-dimensional (2D) local region of an image, binary and nonbinary coding, such as local binary patterns (LBP), local ternary patterns (LTP), and LQP, are used, while the proposed strategy uses three selected directions of mesh patterns to encode the gray scale relationship between the surrounding neighbors for a given center pixel in a 2D image. An innovative aspect of the proposed method is that it makes use of mesh image structure quinary pattern features to encode additional spatial structure information, resulting in better retrieval. On three different kinds of benchmark biomedical data sets, analyses have been completed to assess the viability of MeQryEP. LIDC-IDRI-CT and VIA/I–ELCAP-CT are the lung image databases based on computed tomography (CT), while OASIS-MRI is a brain database based on magnetic resonance imaging (MRI). This method outperforms state-of-the-art texture extraction methods, such as LBP, LQEP, LTP, LMeP, LMeTerP, DLTerQEP, LQEQryP, and so on in terms of average retrieval precision (ARP) and average retrieval rate (ARR).

A real-time defect detection in printed circuit boards applying deep learning

Inspection of defects in the printed circuit boards (PCBs) has both safety and economic significance in the 4.0 industrial manufacturing. Nevertheless, it is still a challenging problem to be studied in-depth due to the complexity of the PCB layouts and the shrinking down tendency of the electronic component size. In this paper, a real-time automated supervision algorithm is proposed to test the PCBs quality among different scenarios. The density of the PCBs layout and the complexity on the surface are analyzed based on deep learning and image feature extraction algorithms. To be more detailed, the ORB feature and the Brute-force matching method are utilized to match perfectly the input images with the PCB templates. After transferring images by aiding the RANSAC algorithm, a hybrid method using modern computer vision algorithms is developed to segment defective areas on the PCBs surface. Then, by applying the enhanced Residual Network –50, the proposed algorithm can classify the groove defects on the surface mount technology electronic components which minimum size up to 1x3 mm. After the training process, the proposed system is capable to categorize various types of overproduced, recycled, and cloned PCBs. The speed of the quality testing operation maintains at a high level with an average precision rate up to 96.29 % in case of good brightness conditions. Finally, the computational experiments demonstrate that the proposed system based on deep learning can obtain superior results and it outperforms several existing works in terms of speed, precision, and robustness

Identification Method for Cone Yarn Based on the Improved Faster R-CNN Model

To solve the problems of high labor intensity, low efficiency, and frequent errors in the manual identification of cone yarn types, in this study five kinds of cone yarn were taken as the research objects, and an identification method for cone yarn based on the improved Faster R-CNN model was proposed. In total, 2750 images were collected of cone yarn samples in real of textile industry environments, then data enhancement was performed after marking the targets. The ResNet50 model with strong representation ability was used as the feature network to replace the VGG16 backbone network in the original Faster R-CNN model to extract the features of the cone yarn dataset. Training was performed with a stochastic gradient descent approach to obtain an optimally weighted file to predict the categories of cone yarn. Using the same training samples and environmental settings, we compared the method proposed in this paper with two mainstream target detection algorithms, YOLOv3 + DarkNet-53 and Faster R-CNN + VGG16. The results showed that the Faster R-CNN + ResNet50 algorithm had the highest mean average precision rate for the five types of cone yarn at 99.95%, as compared with the YOLOv3 + DarkNet-53 algorithm with a mean average precision rate that was 2.24% higher and the Faster R-CNN + VGG16 algorithm with a mean average precision that was 1.19% higher. Regarding cone yarn defects, shielding, and wear, the Faster R-CNN + ResNet50 algorithm can correctly identify these issues without misdetection occurring, with an average precision rate greater than 99.91%.

Content‐based image retrieval for super‐resolutioned images using feature fusion: Deep learning and hand crafted

AbstractAn innovative image retrieval agenda by concatenating deep learning features from GoogleNet and low‐level features from HSI and RGB color space is proposed in this article. Most of the CNN features suffer from loss of information due to image resize as a pre‐processing stage. To reduce this information loss super‐resolution technic is used for resizing images. An improved form of dot‐diffused block truncation coding is used for extracting RGB handcraft features. To discover the interdependencies between color and intensity component of an image, interchannel voting between hue, saturation, and intensity component is calculated as a color feature in HSI space. Histogram of orientated gradient (HOG) feature is used as shape feature. Five standard performance parameters, average precision rate, average recall rate, F‐Measure, Average Normalized Modified Retrieval Rank, and Total Minimum Retrieval Epoch, are applied on nine image datasets: Corel‐1K, Corel‐5K, Corel‐10K, VisTex, STex, ColorBrodatz and three subsets of ImageNet dataset for evaluation process of proposed method. For all dataset the best performance is achieved by the proposed method with respect to all performance parameters.

Clothing Insulation Rate and Metabolic Rate Estimation for Individual Thermal Comfort Assessment in Real Life.

Satisfactory indoor thermal environments can improve working efficiencies of office staff. To build such satisfactory indoor microclimates, individual thermal comfort assessment is important, for which personal clothing insulation rate () and metabolic rate (M) need to be estimated dynamically. Therefore, this paper proposes a vision-based method. Specifically, a human tracking-by-detection framework is implemented to acquire each person’s clothing status (short-sleeved, long-sleeved), key posture (sitting, standing), and bounding box information simultaneously. The clothing status together with a key body points detector locate the person’s skin region and clothes region, allowing the measurement of skin temperature () and clothes temperature (), and realizing the calculation of from and . The key posture and the bounding box change across time can category the person’s activity intensity into a corresponding level, from which the M value is estimated. Moreover, we have collected a multi-person thermal dataset to evaluate the method. The tracking-by-detection framework achieves a mAP50 (Mean Average Precision) rate of 89.1% and a MOTA (Multiple Object Tracking Accuracy) rate of 99.5%. The estimation module gets an accuracy of 96.2% in locating skin and clothes. The M estimation module obtains a classification rate of 95.6% in categorizing activity level. All of these prove the usefulness of the proposed method in a multi-person scenario of real-life applications.

AI-based Automated Extraction of Location-Oriented COVID-19 Sentiments

The coronavirus disease (COVID-19) pandemic has affected the lives of social media users in an unprecedented manner. They are constantly posting their satisfaction or dissatisfaction over the COVID-19 situation at their location of interest. Therefore, understanding location-oriented sentiments about this situation is of prime importance for political leaders, and strategic decision-makers. To this end, we present a new fully automated algorithm based on artificial intelligence (AI), for extraction of location-oriented public sentiments on the COVID-19 situation. We designed the proposed system to obtain exhaustive knowledge and insights on social media feeds related to COVID-19 in 110 languages through AI-based translation, sentiment analysis, location entity detection, and decomposition tree analysis. We deployed fully automated algorithm on live Twitter feed from July 15, 2021 and it is still running as of 12 January, 2022. The system was evaluated on a limited dataset between July 15, 2021 to August 10, 2021. During this evaluation timeframe 150,000 tweets were analyzed and our algorithm found that 9,900 tweets contained one or more location entities. In total, 13,220 location entities were detected during the evaluation period, and the rates of average precision and recall rate were 0.901 and 0.967, respectively. As of 12 January, 2022, the proposed solution has detected 43,169 locations using entity recognition. According to the best of our knowledge, this study is the first to report location intelligence with entity detection, sentiment analysis, and decomposition tree analysis on social media messages related to COVID-19 and has covered the largest set of languages.

Deep Learning for Strawberry Canopy Delineation and Biomass Prediction from High-Resolution Images.

Modeling plant canopy biophysical parameters at the individual plant level remains a major challenge. This study presents a workflow for automatic strawberry canopy delineation and biomass prediction from high-resolution images using deep neural networks. High-resolution (5 mm) RGB orthoimages, near-infrared (NIR) orthoimages, and Digital Surface Models (DSM), which were generated by Structure from Motion (SfM), were utilized in this study. Mask R-CNN was applied to the orthoimages of two band combinations (RGB and RGB-NIR) to identify and delineate strawberry plant canopies. The average detection precision rate and recall rate were 97.28% and 99.71% for RGB images and 99.13% and 99.54% for RGB-NIR images, and the mean intersection over union (mIoU) rates for instance segmentation were 98.32% and 98.45% for RGB and RGB-NIR images, respectively. Based on the center of the canopy mask, we imported the cropped RGB, NIR, DSM, and mask images of individual plants to vanilla deep regression models to model canopy leaf area and dry biomass. Two networks (VGG-16 and ResNet-50) were used as the backbone architecture for feature map extraction. The R 2 values of dry biomass models were about 0.76 and 0.79 for the VGG-16 and ResNet-50 networks, respectively. Similarly, the R 2 values of leaf area were 0.82 and 0.84, respectively. The RMSE values were approximately 8.31 and 8.73 g for dry biomass analyzed using the VGG-16 and ResNet-50 networks, respectively. Leaf area RMSE was 0.05 m2 for both networks. This work demonstrates the feasibility of deep learning networks in individual strawberry plant extraction and biomass estimation.

Content Based Medical Image Retrieval for Accurate Disease Diagnosis

Introduction: Content Based Image Retrieval (CBIR) system is an innovative technology to retrieve images from various media types. One of the CBIR applications is Content Based Medical Image Retrieval (CBMIR). The image retrieval system retrieves the most similar images from the historical cases, and such systems can only support the physician's decision to diagnose a disease. To extract the useful features from the query image for linking similar types of images is the major challenge in the CBIR domain. The Convolution Neural Network (CNN) can overcome the drawbacks of traditional algorithms, dependent on the low-level feature extraction technique. Objective: The objective of the study is to develop a CNN model with a minimum number of convolution layers and to get the maximum possible accuracy for the CBMIR system. The minimum number of convolution layers reduces the number of mathematical operations and the time for the model's training. It also reduces the number of training parameters, like weights and bias. Thus, it reduces the memory requirement for the model storage. This work mainly focused on developing an optimized CNN model for the CBMIR system. Such systems can only support the physicians' decision to diagnose a disease from the images and retrieve the relevant cases to help the doctor decide the precise treatment. Methods: The deep learning-based model is proposed in this paper. The experiment is done with several convolution layers and various optimizers to get the maximum accuracy with a minimum number of convolution layers. Thus, the ten-layer CNN model is developed from scratch and used to derive the training and testing images' features and classify the test image. Once the image class is identified, the most relevant images are determined based on the Euclidean distance between the query features and database features of the identified class. Based on this distance, the most relevant images are displayed from the respective class of images. The general dataset CIFAR10, which has 60,000 images of 10 different classes, and the medical dataset IRMA, which has 2508 images of 9 various classes, have been used to analyze the proposed method. The proposed model is also applied for the medical x-ray image dataset of chest disease and compared with the other pre-trained models. Results: The accuracy and the average precision rate are the measurement parameters utilized to compare the proposed model with different machine learning techniques. The accuracy of the proposed model for the CIFAR10 dataset is 93.9%, which is better than the state-of-the-art methods. After the success for the general dataset, the model is also tested for the medical dataset. For the x-ray images of the IRMA dataset, it is 86.53%, which is better than the different pre-trained model results. The model is also tested for the other x-ray dataset, which is utilized to identify chest-related disease. The average precision rate for such a dataset is 97.25%. Also, the proposed model fulfills the major challenge of the semantic gap. The semantic gap of the proposed model for the chest disease dataset is 2.75%, and for the IRMA dataset, it is 13.47%. Also, only ten convolution layers are utilized in the proposed model, which is very small in number compared to the other pre-trained models. Conclusion: The proposed technique shows remarkable improvement in performance metrics over CNN-based state-of-the-art methods. It also offers a significant improvement in performance metrics over different pre-trained models for the two different medical x-ray image datasets.

Content Based Medical Image Retrieval for Accurate Disease Diagnosis

Introduction: Content Based Image Retrieval (CBIR) system is an innovative technology to retrieve images from various media types. One of the CBIR applications is Content Based Medical Image Retrieval (CBMIR). The image retrieval system retrieves the most similar images from the historical cases, and such systems can only support the physician's decision to diagnose a disease. To extract the useful features from the query image for linking similar types of images is the major challenge in the CBIR domain. The Convolution Neural Network (CNN) can overcome the drawbacks of traditional algorithms, dependent on the low-level feature extraction technique. Objective: The objective of the study is to develop a CNN model with a minimum number of convolution layers and to get the maximum possible accuracy for the CBMIR system. The minimum number of convolution layers reduces the number of mathematical operations and the time for the model's training. It also reduces the number of training parameters, like weights and bias. Thus, it reduces the memory requirement for the model storage. This work mainly focused on developing an optimized CNN model for the CBMIR system. Such systems can only support the physicians' decision to diagnose a disease from the images and retrieve the relevant cases to help the doctor decide the precise treatment. Methods: The deep learning-based model is proposed in this paper. The experiment is done with several convolution layers and various optimizers to get the maximum accuracy with a minimum number of convolution layers. Thus, the ten-layer CNN model is developed from scratch and used to derive the training and testing images' features and classify the test image. Once the image class is identified, the most relevant images are determined based on the Euclidean distance between the query features and database features of the identified class. Based on this distance, the most relevant images are displayed from the respective class of images. The general dataset CIFAR10, which has 60,000 images of 10 different classes, and the medical dataset IRMA, which has 2508 images of 9 various classes, have been used to analyze the proposed method. The proposed model is also applied for the medical x-ray image dataset of chest disease and compared with the other pre-trained models. Results: The accuracy and the average precision rate are the measurement parameters utilized to compare the proposed model with different machine learning techniques. The accuracy of the proposed model for the CIFAR10 dataset is 93.9%, which is better than the state-of-the-art methods. After the success for the general dataset, the model is also tested for the medical dataset. For the x-ray images of the IRMA dataset, it is 86.53%, which is better than the different pre-trained model results. The model is also tested for the other x-ray dataset, which is utilized to identify chest-related disease. The average precision rate for such a dataset is 97.25%. Also, the proposed model fulfills the major challenge of the semantic gap. The semantic gap of the proposed model for the chest disease dataset is 2.75%, and for the IRMA dataset, it is 13.47%. Also, only ten convolution layers are utilized in the proposed model, which is very small in number compared to the other pre-trained models. Conclusion: The proposed technique shows remarkable improvement in performance metrics over CNN-based state-of-the-art methods. It also offers a significant improvement in performance metrics over different pre-trained models for the two different medical x-ray image datasets.

Real-Time Detection and Location of Potted Flowers Based on a ZED Camera and a YOLO V4-Tiny Deep Learning Algorithm

In order to realize the real-time and accurate detection of potted flowers on benches, in this paper we propose a method based on the ZED 2 stereo camera and the YOLO V4-Tiny deep learning algorithm for potted flower detection and location. First, an automatic detection model of flowers was established based on the YOLO V4-Tiny convolutional neural network (CNN) model, and the center points on the pixel plane of the flowers were obtained according to the prediction box. Then, the real-time 3D point cloud information obtained by the ZED 2 camera was used to calculate the actual position of the flowers. The test results showed that the mean average precision (MAP) and recall rate of the training model was 89.72% and 80%, respectively, and the real-time average detection frame rate of the model deployed under Jetson TX2 was 16 FPS. The results of the occlusion experiment showed that when the canopy overlap ratio between the two flowers is more than 10%, the recognition accuracy will be affected. The mean absolute error of the flower center location based on 3D point cloud information of the ZED 2 camera was 18.1 mm, and the maximum locating error of the flower center was 25.8 mm under different light radiation conditions. The method in this paper establishes the relationship between the detection target of flowers and the actual spatial location, which has reference significance for the machinery and automatic management of potted flowers on benches.

Hybrid lightweight Deep-learning model for Sensor-fusion basketball Shooting-posture recognition

Shooting-posture recognition is an important area in basketball technical movement recognition domain. This paper proposes the squeeze convolutional gated attention (SCGA) deep-learning model to try identifying various sensor-fusion basketball shooting postures. The model is based on the lightweight SqueezeNet deep-learning model for spatial feature extraction, the gated recurrent unit for time-series feature extraction, and an attention mechanism for feature-weighting calculation. The SCGA model is used to train and test the 10 types of sensor-fusion basketball shooting-posture datasets, and the intra-test achieved an average precision rate of 98.79%, an average recall rate of 98.85%, and a Kappa value of 0.9868. The inter-test achieved a 94.06% average precision rate, 94.57% average recall rate, and a 0.9389 Kappa value. The effectiveness of the SCGA deep-learning model illustrates the potential of the proposed model in recognizing various sensor-fusion basketball shooting postures. This study provides a reference for the field of sports technical-movement recognition.

Classification of Tweets Causing Deadlocks in Jakarta Streets with the Help of Algorithm C4.5

Congestion seems to be a daily occurrence in the Indonesian city of Jakarta. As a consequence, the rider has access to essential information regarding traffic conditions at all times, which is beneficial. Through social media platforms such as Twitter, this information is readily available to the public. On the other hand, the information offered on Twitter is still uncategorized text. DKI Jakarta, as a consequence, developed a congestion classification system that included data mining techniques, a classification approach based on the decision tree technique, and C4.5 as a component. This C4.5 method transforms a large amount of information into a decision tree that shows the rules. Geocoding will be utilized to illustrate the locations that have been gathered, and a data split with a confusion matrix will be used to assess how well the categorization process has worked. According to the study's results, the average accuracy rate is 99.08 percent, the average precision rate is 99.46 percent, and the average recall rate is 97.99 percent.

Bolt defect classification algorithm based on knowledge graph and feature fusion

At present, there is a problem of insufficient utilization of regional features in the application of the existing knowledge graph based on GGNN in the defect classification of the bolt and nut pair of transmission lines. Therefore, a decision-making method of combining the bolt and nut pair with the original regional feature and the bolt and nut pair knowledge graph feature is proposed. For this reason, a method is proposed to combine the decision-making of the bolt and nut pair on the original regional features and the bolt and nut pair on the characteristics of the knowledge graph. First, the characteristics of the bolt and nut pair knowledge graph are combined with the adaptive normalization of the bolt and nut pair to the features of the original area. Then, the classification score vector based on fusion features and the classification score vector based on the bolt and nut pair to the original area feature are derived from the classifier respectively; Finally, the classification score vector of the fusion feature and the bolt and nut pair are fused to the classification score vector of the original region feature to obtain the final classification result. On this basis, this article uses bolt and nut pair to conduct multiple sets of defect classification experiments on the data set of the knowledge graph experiment. The experimental results show that the method of decision fusion of the bolt and nut pair to the original regional feature fusion the bolt and nut pair to the knowledge graph feature is better than the bolt and nut pair to the knowledge graph average precision, precision, and recall rate. It is effective Prove the improvement of the algorithm.

Improved Content Based Image Retrieval Process Based on Deep Convolutional Neural Network and Salp Swarm Algorithm

Digital image and medical image retrieval from several repositories are improving gradually, so the capacity of repositories increases rapidly. The semantic space is the main issue on content-based image retrieval (CBIR), which exists among the semantic level as well as increases the data recognized through human and low level visible data obtained through the image. The CBIR system utilizes the deep convolutional neural network (DCNN), which is trained to medical image characterization and the digital image by salp swarm optimization algorithm (SSA). The average classification accuracy for medical image is 86.805%, a mean average precision is 79%, Average Recall Rate (ARR) is 91.7% and [Formula: see text]-measure is 84.9%, are achieved during retrieval task. For image retrieval, the Average Precision Rate (APR) improved from 39%, 40%, 36% and 42.5% to 86.8% and the ARR enhanced from 39.5%, 40.5%, 35.5% and 42.5% to 86.8%. The [Formula: see text]-measure is improved from 39.5%, 40.5%, 35.5% and 42.5% to 86.8% as different with Local tetra patterns (LTrP), LOOP, local derivative pattern (LDP) and local mean differential excitation pattern (LMDeP) separately on Corel-1K dataset. The presented method is most suitable for multimodal digital images and medical image retrieval for various parts of the body.

Content-based image retrieval using feature-fusion of GroupNormalized-Inception-Darknet-53 features and handcraft features

This paper proposed an efficient image retrieval framework by feature-fusion of high-level features from the improved version of DarkNet-53, named GroupNormalized-Inception-Darknet-53 (GN-Inception-Darknet-53), and handcraft features extracted from both RGB and HSI color models. To extract the more detailed features of an image, we augmented one inception layer, which includes 1 × 1, 3 × 3, and 5 × 5 kernels in place of an existing 3 × 3 kernel. To make the normalization process of the proposed model less dependent on batch size, Group Normalization (GN) layer is used instead of Batch Normalization (BN). A modified version of dot-diffused block truncation coding (DDBTC) is used to extract handcraft features in RGB color space. For HSI color space, interchannel voting between hue, saturation, and intensity components is used as color feature. To extract shape features histogram of orientated gradient (HOG) is applied on RGB color space. To evaluate the efficiency of our proposed method, Average Precision Rate (APR), Average Recall Rate (ARR), F-Measure, Average Normalized Modified Retrieval Rank (ANMRR), and Total Minimum Retrieval Epoch (TMRE) are calculated for Corel-1 K, Corel-5 K, Corel-10 K, VisTex, Stex & Color Brodatz datasets. In all datasets, the proposed method shows the best results for all the instances with a minimum average improvement of 7.02%.

Recognition of Fetal Facial Ultrasound Standard Plane Based on Texture Feature Fusion.

In the process of prenatal ultrasound diagnosis, accurate identification of fetal facial ultrasound standard plane (FFUSP) is essential for accurate facial deformity detection and disease screening, such as cleft lip and palate detection and Down syndrome screening check. However, the traditional method of obtaining standard planes is manual screening by doctors. Due to different levels of doctors, this method often leads to large errors in the results. Therefore, in this study, we propose a texture feature fusion method (LH-SVM) for automatic recognition and classification of FFUSP. First, extract image's texture features, including Local Binary Pattern (LBP) and Histogram of Oriented Gradient (HOG), then perform feature fusion, and finally adopt Support Vector Machine (SVM) for predictive classification. In our study, we used fetal facial ultrasound images from 20 to 24 weeks of gestation as experimental data for a total of 943 standard plane images (221 ocular axial planes, 298 median sagittal planes, 424 nasolabial coronal planes, and 350 nonstandard planes, OAP, MSP, NCP, N-SP). Based on this data set, we performed five-fold cross-validation. The final test results show that the accuracy rate of the proposed method for FFUSP classification is 94.67%, the average precision rate is 94.27%, the average recall rate is 93.88%, and the average F1 score is 94.08%. The experimental results indicate that the texture feature fusion method can effectively predict and classify FFUSP, which provides an essential basis for clinical research on the automatic detection method of FFUSP.

Spelling Correction Real-Time American Sign Language Alphabet Translation System Based on YOLO Network and LSTM

In this paper, we present a novel approach that aims to solve one of the main challenges in hand gesture recognition tasks in static images, to compensate for the accuracy lost when trained models are used to interpret completely unseen data. The model presented here consists of two main data-processing stages. A deep neural network (DNN) for performing handshape segmentation and classification is used in which multiple architectures and input image sizes were tested and compared to derive the best model in terms of accuracy and processing time. For the experiments presented in this work, the DNN models were trained with 24,000 images of 24 signs from the American Sign Language alphabet and fine-tuned with 5200 images of 26 generated signs. The system was real-time tested with a community of 10 persons, yielding a mean average precision and processing rate of 81.74% and 61.35 frames-per-second, respectively. As a second data-processing stage, a bidirectional long short-term memory neural network was implemented and analyzed for adding spelling correction capability to our system, which scored a training accuracy of 98.07% with a dictionary of 370 words, thus, increasing the robustness in completely unseen data, as shown in our experiments.