Average Retrieval Accuracy Research Articles

Web log mining techniques to optimize Apriori association rule algorithm in sports data information management

To optimize the current college sports data information management system, this study combines the Apriori association rule algorithm with web application development technology to upgrade the management system. Firstly, this study explores novel log mining techniques in genetic algorithms and web application development technology. Secondly, by integrating log mining techniques to optimize the Apriori algorithm, associations between sports data and information are discovered. Through the optimized algorithm, this study identifies key association rules of sports data information and validates the optimized system’s reliability and effectiveness through experiments. The experimental results show that the running time of the traditional Apriori algorithm exponentially grows with the increase in information volume, while the optimized execution efficiency is improved by approximately 10–15%. Additionally, the average retrieval accuracy of this optimized system can reach 98.3%, although the retrieval time also increased by 23%. Therefore, the technology and algorithms proposed in this study have certain application value in the sports information management system and contribute to the optimization of data information management in this field.

Image Retrieval Using Fusion of Sauvola and Thepade’s Sorted Block Truncation Coding-Based Color Features

Because of the tremendous growth in digital imaging, enhanced communication and storage technology, billions of images are captured, stored, and exchanged daily. Finding and searching for an image in a large collection is becoming challenging. The query by reference image retrieval (IR) technique aims to close the semantic gap between the query and retrieve images while improving performance. The primary goal of the work proposed here is to develop discriminative and descriptive features of the image with the minimum possible size. Here, the weighted feature fusion-based IR technique is proposed using Sauvola local thresholding (SLT) and Thepade’s Sorted Block Truncation Coding (SBTC) methods. The proposed technique is tested using two standard datasets with mean square error (MSE) as a distance measure and average retrieval accuracy (ARA) as a performance metric. The technique has contributed to the enhancement of ARA with the small and fixed-size image feature vector. The feature vector generated is much smaller than the image dimension and is used as a feature vector to represent the image for retrieval. Results prove that the proposed technique of SBTC 8-ary with 0.1 weight and SLT with 0.9 weight feature fusion gives better ARA than other techniques studied.

Sea surface temperature retrieval based on simulated space-borne one-dimensional multifrequency synthetic aperture microwave radiometry

The space-borne one-dimensional multifrequency synthetic aperture microwave radiometer (1D-MSAMR) offers new possibilities for detecting high spatial resolution sea surface temperature (SST). To achieve higher SST retrieval accuracy, an SST retrieval algorithm, the two-step retrieval algorithm (TSSR), is proposed based on the multiple linear regression (MLR) algorithm. In this study, we investigated the SST retrieval accuracy of 1D-MSAMR based on simulation experiments. For the study, we assumed that the frequencies of the 1D-MSAMR were 6.9, 10.65, 18.7, 23.8, and 36.5 GHz, and that all frequencies worked in a dual polarization (vertical and horizontal) manner. We used an ocean-atmosphere microwave radiation brightness temperature model and the 1D-MSAMR simulator to simulate the measured brightness temperature based on WindSat data provided by the Remote Sensing Systems (RSS). An MLR algorithm and the TSSR were then developed to retrieve the SST within the incidence angle range of 0°–65°. The results show that the SST retrieval errors of the two SST retrieval algorithms decreased with the increase of incidence angle. The TSSR had higher retrieval accuracy, especially at low incidence angle. The average retrieval accuracy of the TSSR was about 0.3 K higher than that of the MLR algorithm. The retrieval error of the TSSR was also less sensitive to the measurement error of the 6.9 GHz frequency than the MLR algorithm.

BIM Style Restoration Based on Image Retrieval and Object Location Using Convolutional Neural Network

BIM is one of the main technical ways to realize building informatization, and the model’s texture is essential to its style design during BIM construction. However, the texture maps provided by mainstream BIM software are not realistic enough and monotonous to meet the actual needs of users for the model style. Therefore, an interior furniture BIM style restoration method was proposed based on image retrieval and object location using convolutional neural network. First, two types of furniture images, namely grayscale contour images from BIM software and real images from the Internet, were collected to train the following network model. Second, a multi-feature weighted fusion neural network model based on an attention mechanism (AM-rVGG) was proposed, which focused on the structural information of furniture images to retrieve the most similar real image, and then some furniture image patches from the retrieved one were generated with object location and random cropping techniques as the candidate texture maps of the furniture BIM. Finally, the candidate ones were fed back into the BIM software to realize the restoration of the furniture BIM style. The experimental results showed that the average retrieval accuracy of the proposed network model was 83.1%, and the obtained texture maps could effectively restore the real style of the furniture BIM. This work provides a new idea for restoring the realism in other BIM.

VF‐EFENet: A novel method for environmental sound filtering and feature extraction

To solve the problems such as low accuracy and low retrieval performance in feature extraction of environmental sound data from Internet consumer finance scenario, a novel method for environmental sound filtering and feature extraction (VF-EFENet) is proposed. First, the Conv-TasNet speech separation model is clipped and migrated to filter foreground voice. Second, an environmental sound feature extraction model is established based on the improved VGGish, and pretraining weight is used to improve the feature extraction accuracy. Finally, metric learning is used to optimize the distance function to improve retrieval accuracy. Metric learning can make the same kind of audio feature space cohesive and the different types of audio feature space away. The experiments are implemented based on AISHELL-1 and ESC-50 data sets to test voice filter performance, average classification accuracy and average retrieval accuracy. The experimental results show that VF-EFENet can effectively filter the voice in mixed audio and the SI-SNR reaches 12.51 db. When sampling rate is 8 kHz, the average classification accuracy is improved by 8.3% after voice filtering using VF-EFENet. When Top30 samples are retrieved, the average retrieval accuracy of VF-EFENet is 7.37% higher than that of ESResNetAttention.

Ancient Chinese Character Image Retrieval Based on Dual Hesitant Fuzzy Sets

The complex and changeable structures of ancient Chinese characters result in the decreasing accuracy of their image retrieval. To resolve this problem, a new retrieval method based on dual hesitant fuzzy sets is proposed. Dual hesitation fuzzy sets that can express uncertain information more comprehensively are employed in the feature extraction process of directional line elements. The multiattribute evaluation index of adjacent grids for the current grid and its corresponding membership and nonmembership functions are established, and the weight of each attribute is calculated by the dual hesitation fuzzy entropy, such that the proposed features can fully reflect the topological structure of ancient Chinese characters. Using the dual hesitation fuzzy correlation coefficient to measure the similarity between the ancient Chinese character images to be retrieved and the candidate images, the retrieval of ancient Chinese character images is realized. Experiments show that when the t0hreshold value of the correlation coefficient is 0.9, the average retrieval accuracy is 90.4%.

Directional Magnitude Local Hexadecimal Patterns: A Novel Texture Feature Descriptor for Content-Based Image Retrieval

Social media platforms such as Twitter, Facebook, and Flicker, and the evolution of digital image capturing devices have resulted in the generation of a massive number of images. Thus, we experienced an exponential growth in digital image repositories in the last decade. Content-based image retrieval (CBIR) has been extensively employed to reduce the dependency on textual annotations for image searching. Effective feature descriptor is mandatory to retrieve the most relevant images from the repository. Additionally, CBIR methods often experience the semantic gap problem, which must also be addressed. In this paper, we propose a novel texture descriptor, Directional Magnitude Local Hexadecimal Patterns (DMLHP), based on the texture orientation and magnitude to retrieve the most relevant images. The objective of the proposed feature descriptor is to examine the relationship between the neighboring pixels and their adjacent neighbors based on texture orientation and magnitude. Our DMLHP texture descriptor is capable of capturing the texture and semantic information of the images effectively with the same visual content. Furthermore, the proposed method employs a learning-based approach to lessen the semantic gap problem and to improve the understanding of the contents of query images to retrieve the most relevant images. The presented descriptor provides remarkable results by achieving the average retrieval precision (ARP) of 66%, 92%, 83%, average retrieval recall (ARR) of 66%, 92%, 83%, average retrieval specificity (ARS) of 99%, 99%, 76%, and average retrieval accuracy (ARA) of 98%, 99%, 85% on the AT&T, MIT Vistex, and Brodatz Texture image repositories, respectively. Our experiments reveal that the proposed DMLHP descriptor achieves far better performance, i.e., 95% on AT&T, 92% on BT, and 99% on MIT Vistex, when used with a learning-based approach over a non-learning-based approach (similarity measure). Experimental results show that the proposed texture descriptor outperforms state-of-the-art descriptors such as LNIP, LTriDP, LNDP, LDGP, LEPSEG, and CSLBP for CBIR.

A novel image-based retrieval system for characterization of maxillofacial lesions in cone beam CT images.

The objective of medical content-based image retrieval (CBIR) is to assist clinicians in decision making by retrieving the most similar cases to a given query image from a large database. Herein, a new method for content-based image retrieval of cone beam CT (CBCT) scans is presented. The introduced framework consists of two main phases: training database construction and querying. The goal of the training phase is database construction, which consists of three main steps. First, automatic segmentation of lesions using 3D symmetry analysis is performed. Embedding the prior shape knowledge of the 3D symmetry characteristics of the healthy human head structure increases the accuracy of automatic segmentation. Then, spatial pyramid matching is used for feature extraction, and the relative importance of each feature is learned using classifiers. The method was applied to a dataset of 1145 volumetric CBCT images with four classes of maxillofacial lesions. A symmetry-based analysis model for automatic lesion segmentation was evaluated using similarity measures. Mean Dice coefficients of 0.89, 0.85, 0.92, and 0.87 were achieved for maxillary sinus perforation, radiolucent lesion, unerupted tooth, and root fracture classes, respectively. Moreover, the execution time of automatic segmentation was reduced to 3min per case. The performance of the proposed search engine was evaluated using mean average precision and normalized discounted cumulative gain. A mean average retrieval accuracy and normalized discounted cumulative gain of 0.90 and 0.92, respectively, were achieved. Quantitative results show that the proposed approach is more effective than previous methods in the literature, and it can facilitate the introduction of CBIR in clinical CBCT applications.

Image Retrieval Using CBIR Including Light Position Analysis

We propose a method for estimating the weight of the light source position to content-based image retrieval (CBIR) through retrieving image data. The image retrieval method makes use of a multi-dimensional descriptor expressing the features of the image. A multi-directional Gabor filter is then applied in order to extract the contour direction of the image, and a color correlation is applied in order to analyze the distribution of the position between the colors in the image. An HSV histogram and chromatic distribution information were obtained for the color composition analysis, and the light source position in the image was estimated for the main region extraction. The relative similarity between the images was measured through a relative comparison between each descriptor. In conventional image retrieval, there is a disadvantage in terms of the large computational intensity required, because the accuracy is degraded when simple information is used or when the result is estimated through a comparison of complex image components. However, the proposed method adds a light source location analysis element in order to ensure accurate retrieval. Image retrieval using the proposed method achieves an average retrieval accuracy of 85%, indicating that its reliability is superior to that of previously described methods.

A novel image retrieval scheme using gray level co-occurrence matrix descriptors of discrete cosine transform based residual image

Several CBIR schemes have been devised by the formation of the low dimensional image feature vector from the primitive visual features such as color, texture and/or shape of the image to speed up the retrieval process. In this paper, the visual contents of the images have been extracted using block level Discrete Cosine Transformation (DCT) and Gray Level Co-occurrence Matrix (GLCM). Since the DC coefficients based feature vector has retained the most significant visual components of the image, so initially, we have computed DC coefficients based uniform quantized histogram and some statistical parameters are derived from that histogram for the formation of the DC feature vector. Subsequently, other significant visual features are computed from the residual image where the residual image is obtained by taking the difference between the original image plane and the DC coefficients based reconstructed image plane. Thereafter, some statistical parameters from GLCMs of the residual image are considered for the construction of the GLCM based feature vector. This feature vector is suitable to identify the texture features of the residual image in a more effective way. The single feature vector has been obtained by combining DC and GLCM feature vectors since the combined extracted features from the images increase the accuracy of any image retrieval system. We have tested the scheme either in intensity image or on three color planes of an RGB color image. The experimental results are evaluated on two standard image databases and demonstrate the effectiveness of the proposed scheme in terms of average retrieval accuracy. In addition, the overall speed of the proposed CBIR system is high due to the formation of the low dimensional significant feature vector. The comparative results also show that the proposed scheme provides effective accuracy than some other state-of-the-art CBIR schemes.

A fully automatic end-to-end method for content-based image retrieval of CT scans with similar liver lesion annotations.

The goal of medical content-based image retrieval (M-CBIR) is to assist radiologists in the decision-making process by retrieving medical cases similar to a given image. One of the key interests of radiologists is lesions and their annotations, since the patient treatment depends on the lesion diagnosis. Therefore, a key feature of M-CBIR systems is the retrieval of scans with the most similar lesion annotations. To be of value, M-CBIR systems should be fully automatic to handle large case databases. We present a fully automatic end-to-end method for the retrieval of CT scans with similar liver lesion annotations. The input is a database of abdominal CT scans labeled with liver lesions, a query CT scan, and optionally one radiologist-specified lesion annotation of interest. The output is an ordered list of the database CT scans with the most similar liver lesion annotations. The method starts by automatically segmenting the liver in the scan. It then extracts a histogram-based features vector from the segmented region, learns the features' relative importance, and ranks the database scans according to the relative importance measure. The main advantages of our method are that it fully automates the end-to-end querying process, that it uses simple and efficient techniques that are scalable to large datasets, and that it produces quality retrieval results using an unannotated CT scan. Our experimental results on 9 CT queries on a dataset of 41 volumetric CT scans from the 2014 Image CLEF Liver Annotation Task yield an average retrieval accuracy (Normalized Discounted Cumulative Gain index) of 0.77 and 0.84 without/with annotation, respectively. Fully automatic end-to-end retrieval of similar cases based on image information alone, rather that on disease diagnosis, may help radiologists to better diagnose liver lesions.

Extended Case-Based Behavior Control for Multi-Humanoid Robots

Intelligent control of multi-agent autonomous humanoid robots is a very complex problem, especially in the RoboCup domain. This is due to the dynamics of the environment and the complexity of behaviors that should be executed in real time. Moreover, the overall complexity increases since another mechanism for coordinating the robot’s behaviors should be involved. Throughout the past years, acceptable results have been obtained using different approaches to solve the behavior control problem (decision trees, fuzzy techniques, support vector machines, reinforcement learning, etc.). As case-based reasoning (CBR) is tightly related to the way humans reason, researches are now concentrated on finding the most relevant solutions that could handle behavior control problems of humanoid soccer robots using CBR techniques. This paper proposes an extended algorithm of a more complex architecture to control more complex soccer behaviors such as dribbling and goal scoring applied to multi-robot scenarios between attacker and goalie. The decomposition of features into a hierarchy of levels has led to reduced complexity of the overall behavior execution in real time. However, the average retrieval accuracy and the average performance accuracy were relatively low (70.3% and 77%, respectively). We intend to combine neural networks with CBR to learn adaptation rules for reducing the complexity of hand-coded rules and improving the overall controller performance.

Studying the impact of sequence clustering on near-duplicate video retrieval: an experimental comparison

In this paper, we propose studying the impact of clustering on near-duplicate video (NDV) retrieval. The aim is to reduce the search space at retrieval time through a pre-processing clustering step performed on the dataset off-line and retrieving NDVs based on the formed clusters. Our contribution is a novel clustering framework inspired by a bioinformatics technique, namely DNA multiple sequence alignment (MSA). A series of video keyframes in chronological order is represented as an alphabetical genome, analogous to a DNA sequence and MSA is employed to automatically partition the NDVs in a video collection into clusters. After discussing the advantages and shortcomings of the main state-of-the-art clustering approaches for video clustering in the theoretical part of the paper, we empirically evaluate the performance of the proposed MSA-based framework against five clustering algorithms representative of these mainstream approaches: Birch, Cure, Dbscan, Expectation-Maximization and Proclus. Also, we show that our clustering-based approach, while being significantly faster than non-clustering-based n-gram and edit distance NDV retrieval techniques, yields better mean average precision retrieval accuracy.

Fusing magnitude and phase of wavelet moments for content-based image retrieval

The wavelet moments (WMs) are capable to represent the variations in the images as they provide both time and frequency localisation. In this paper the image retrieval system is implemented using complex wavelet moments (CWMs). The magnitude of the WMs of image is rotation invariant, but the phase component changes with image rotation. The magnitude and phase of WMs are incorporated and used both real and imaginary components of WMs so as to make WMs complex to describe as image. The rotation invariance of real and imaginary component is achieved by correction and comparison of phases of WMs of two comparable images with suitable distance metric. The proposed algorithm is applied to USC Rotated Texture database and Colombia Object Image Library (COIL-100) database and detailed analysis is carried out and performance is compared with other orthogonal moments. In many cases the complex WMs produce excellent performance. The average retrieval accuracy for 13 textures, Bark, Brick, Bubble, Grass, Leather, Pigskin, Raffia, Sand, Straw, Water, Weave, Wood and Wool are 100, 85, 92, 99, 91, 92, 95, 97, 76, 94, 99, 74, and 95% respectively. Also, the experimental results on COIL-100 database reveals that the complex wavelet moment outperforms than complex Zernike moments and it is one of the useful descriptor for content-based image retrieval systems.

Fusion framework for effective color image retrieval

This paper presents a novel framework for color image retrieval through combination of all the low level features, which gives higher retrieval accuracy. The Color Difference Histogram (CDH) and Angular Radial Transform (ART) features are exploited to capture color, texture and shape information of an image. The CDH algorithm is modified in order to make the proposed system more effective. The proposed fusion framework combines the ranking results of the aforementioned descriptors through various post-classification methods i.e. Borda Count method, Min–max and Z-score normalization. The maximum retrieval accuracy attained in terms of average precision using Min–max normalization on Wang’s database is 78.3% when ART is applied on non-overlapping regions of the images. The proposed fusion framework is recommended because it improves the average retrieval accuracy by approximately 16% and 14% over CDH and ART respectively. Extensive experiments are carried out on different databases to establish the efficacy of the proposed scheme.

Image retrieval based on combined features of interest points

Due to the spatial distribution expression power of the ring areas,this paper proposed a new image retrieval algorithm based on color feature and texture feature of interest points,introducing the ring area into the Gabor wavelet texture features.At first,this algorithm used adaptive smoothing filter to eliminate noises and detected interest points by the Speeded Up Robust Feature(SURF) operator.Then,it calculated the color histogram and texture feature of interest points in the ring area,as image's combined features.Finally,it output similar images according to the similarity of the combined features.The experimental results show that this algorithm improves the average retrieval accuracy by more than 7%.

Texture Image Retrieval Based on NSCT and DT-CWT

Abstract This paper presents a novel algorithm for texture image retrieval based on nonsubsampled contourlet(NSCT) and Dual-tree complex wavelet transform(DT-CWT). Nonsubsampled contourlet transform has anisotropy and translation invariability. DT-CWT not only has good localization in time-frequency domain, but also has approximate translation invariant, more directivity and limited data redundancy. Texture features based on NSCT and DT-CWT can include more information of image. This paper also presents a novel similarity measure. Experimental results demonstrate that the proposed approach improves average retrieval accuracy.

Use of Soil Moisture Variability in Artificial Neural Network Retrieval of Soil Moisture

Passive microwave remote sensing is one of the most promising techniques for soil moisture retrieval. However, the inversion of soil moisture from brightness temperature observations is not straightforward, as it is influenced by numerous factors such as surface roughness, vegetation cover, and soil texture. Moreover, the relationship between brightness temperature, soil moisture and the factors mentioned above is highly non-linear and ill-posed. Consequently, Artificial Neural Networks (ANNs) have been used to retrieve soil moisture from microwave data, but with limited success when dealing with data different to that from the training period. In this study, an ANN is tested for its ability to predict soil moisture at 1 km resolution on different dates following training at the same site for a specific date. A novel approach that utilizes information on the variability of soil moisture, in terms of its mean and standard deviation for a (sub) region of spatial dimension up to 40 km, is used to improve the current retrieval accuracy of the ANN method. A comparison between the ANN with and without the use of the variability information showed that this enhancement enables the ANN to achieve an average Root Mean Square Error (RMSE) of around 5.1% v/v when using the variability information, as compared to around 7.5% v/v without it. The accuracy of the soil moisture retrieval was further improved by the division of the target site into smaller regions down to 4 km in size, with the spatial variability of soil moisture calculated from within the smaller region used in the ANN. With the combination of an ANN architecture of a single hidden layer of 20 neurons and the dual-polarized brightness temperatures as input, the proposed use of variability and sub-region methodology achieves an average retrieval accuracy of 3.7% v/v. Although this accuracy is not the lowest as comparing to the research in this field, the main contribution is the ability of ANN in solving the problem of predicting “out-of-range” soil moisture values. However, the applicability of this method is highly dependent on the accuracy of the mean and standard deviation values within the sub-region, potentially limiting its routine application.