Connected Component Method Research Articles

Automatic Watershed Segmentation of Cancerous Lesions in Unsupervised Breast Histology Images

Segmentation of nuclei in histology images is key in analyzing and quantifying morphology changes of nuclei features and tissue structures. Conventional diagnosis, segmenting, and detection methods have relied heavily on the manual-visual inspection of histology images. These methods are only effective on clearly visible cancerous lesions on histology images thus limited in their performance due to the complexity of tissue structures in histology images. Hence, early detection of breast cancer is key for treatment and profits from Computer-Aided-Diagnostic (CAD) systems introduced to efficiently and automatically segment and detect nuclei cells in pathology. This paper proposes, an automatic watershed segmentation method of cancerous lesions in unsupervised human breast histology images. Firstly, this approach pre-processes data through various augmentation methods to increase the size of dataset images, then a stain normalization technique is applied to these augmented images to isolate nuclei features from tissue structures. Secondly, data enhancement techniques namely; erosion, dilation, and distance transform are used to highlight foreground and background pixels while removing unwanted regions from the highlighted nuclei objects on the image. Consequently, the connected components method groups these highlighted pixel components with similar intensity values and, assigns them to their relevant labeled component binary mask. Once all binary masked groups have been determined, a deep-learning recurrent neural network from the Keras architecture uses this information to automatically segment nuclei objects with cancerous lesions and their edges on the image via watershed filling. This segmentation method is evaluated on an unsupervised, augmented human breast cancer histology dataset of 11,151 images. This proposed method produced a significant evaluation result of 98% F1-accuracy score.

A method for measuring hairline length and discriminating hairline recession grades based on the BiSeNet model

Abstract Hair plays an important role in a person’s appearance. According to a survey by the World Health Organization, approximately 70% of adults have scalp and hair prob lems. Doctors currently make hairline recession diagnoses based on hair loss criteria, but this approach is subjective. This paper proposes a novel method for objectively assessing hairline recession grades. First, the Bilateral Segmentation Network model (BiSeNet) is utilized to obtain a facial segmentation image. Second, this paper utilizes the connected components method to improve the facial segmentation results. Next, the labeling key points method is used to extract part of the features of the eyebrow and facial region and calculate the related values. Finally, the judgment of hairline length and hairline recession grade is realized by combining these features with camera calibration. In this paper, front-face images of 50 volunteers were collected for hair line recession grade determination. The judgment results of expert doctors on hairline length and hairline recession grade were compared with the judgment results of this method. The results showed a 1.3 cm difference in the average length of the hairline and about 80% similarity in hairline recession grade judgments. In conclusion, using machine vision methods to measure the height of the hairline provides objective and repeatable results.

COMPREHENSIVE POTHOLE DETECTION SYSTEM FOR ROAD MAINTENANCE AND SAFETY USING IMAGE PROCESSING AND STEREO VISION

This paper introduces a systematic approach to pothole detection, emphasizing its significance in road maintenance and safety. The proposed system is comprised of meticulously designed modules that collectively contribute to achieving accurate and effective results. Commencing with data collection through cameras capturing road areas of interest, the images undergo manual cropping and resizing for standardization. The core principle of the system revolves around image enhancement, involving grayscale conversion, application of blurring techniques, and adjustments to brightness and contrast. Automatic thresholding extracts essential information encoded within pixels, paving the way for precise edge detection refined through morphological operations. The focus then shifts to pothole detection, incorporating a stereo camera setup to calculate depth and disparity of road surfaces. Critical steps, including image rectification, correspondence matching, and disparity calculations, contribute to the accurate identification and delineation of potholes using depth thresholds. Subsequent modules employ K-Means clustering to segregate regions of interest from the image background, and post-processing steps, including filtering, masking, and refinement, fine-tune the images. Utilizing the HSV color space for grayscale image refinement and the connected component method to isolate white pixel objects further enhance the system's capability. The final step involves the addition of bounding boxes around identified potholes, streamlining their identification process. This comprehensive methodology ensures effective image processing, precise pothole detection, and contributes significantly to road safety and maintenance efforts.

Deteksi Plat Nomor Menggunakan Connected Components dan Pra-Pengolahan untuk Mempercepat Proses Deteksi

As the number of vehicles in Indonesia increases, the number of crimes that occur also increases, resulting in an increase in the problem of traffic violations and an increase in the number of vehicle parking activities. Seeing the importance of number plate detection to overcome this, a system that is able to detect number plates quickly and accurately is needed. The segmentation process using Connected Components has better performance when compared to Diff and Fast-RNN methods. Pre-processing is an important step before carrying out a number plate detection. begins by changing the image size using the resizing function and by converting the RGB image into a grayscale image which aims to reduce the image size, thereby speeding up the next process. Then the segmentation process uses the connected components method. The test results on 10 test images produce an accuracy of 80%. In terms of detection time, it shows a decrease. The number plate detection process without using pre-processing takes an average of 3.721519 seconds, whereas when using pre-processing only 1.45731 seconds. It can be concluded that the addition of pre-processing is able to speed up the detection process

Extraction of Text From Image

Picture Text is the content data implanted or written in picture of various structure. Picture text can be found in caught pictures, filtered records, magazines, papers, banners and so on These picture messages are profoundly accessible these days and they are vital in addressing, depicting and moving data which help people groups in correspondence, tackling issues, accessibility, formation of new sorts of occupations, cost viability, efficiency, globalization and social hole and so forth The data from these picture archives would give higher proficiency and straightforward entry on the off chance that it is changed over to message structure. The cycle by which Image Text changed over into plain content is Text Extraction. Text Extraction is helpful in data recovering, looking, altering, recording, filing or detailing of picture text. In any case, variety of these writings because of contrasts in size, direction style, and arrangement, text is installed in complex hued archive pictures, corrupted reports picture, inferior quality picture, as well as low picture differentiation and complex foundation make issue text extraction incredibly troublesome what's more, testing one. Various strategies like Connected Component Method, Mathematical Morphology Method, Edged Based Method and Texture Based Method have been utilized beforehand, however those all have their own constraints when estimated by various boundaries like exactness, review and f- score. In this paper, text extraction from picture reports, utilizing blend of the two amazing techniques Connected Component and Edge Based Method, to improve execution and exactness of text extraction is talked about and execution is finished by incorporated MATLAB code with MATLAB/Simulink device and the proposed framework is tried by Digital Image Binarization Competition (DIBCO) 2017 dataset. At long last, the separated and perceived is changed over to discourse for legitimate use for outwardly hindered individuals.

The Study of Plate Number Recognition for Parking Security System

Car Plate Number Recognition System is an important platform that can be used to identify a car vehicle identity. The Recognition System is based on image processing techniques and computer vision. A webcam is used to capture an image of the car plate number from different distance, and the identification is conducted through four processes of stages: Image Acquisition Pre-processing, Extraction, Segmentation, and Character Recognition. The Acquisition Pre-processing stage is extracted the region of interest of the image. The image is captured by live video of the webcam, then converted to grayscale and binary image. The Extraction stage is extracted the plate number characters from binary image using a connected components method. In the Segmentation stage is done by implementing horizontal projection as well as moving average filter. Lastly, in the Character Recognition, is used to identify the segmented characters of the plate number using optical character recognition. The proposed method is worked well for Malaysian's private cars plate number, and can be implemented in car park system to increase level of security of the system by confirming the bar code of the parking ticket and the plate number of the car at the incoming and outgoing gates.

SIFT and HOG features for the retrieval of ancient Kannada epigraphs

In this work, the authors presented the indexing method for efficient retrieval of Kannada characters. Here the characters were segmented by the connected component method. Then features were extracted by scale invariant feature transform (SIFT) and histogram of oriented gradients (HOG) methods. These features were condensed by principal component analysis. They presented the indexing approach using K-dimensional tree (K-D tree) to improve the identification process. For the experiment, they used their own database. The results of the experiment show that the indexing prior is faster than conventional identification approaches in terms of time to script. From experimentation, they observe that fusion features achieve the maximum accuracy of 90% with varying principal component analysis features.

Kurtosis-based connected components method for detecting small and transparent foreign objects in semiopaque bottles

In recent years, driven by new standards and image brand, product quality has become highly critical in the food industry. Particularly concerning the beverage industry, the potential presence of very small foreign objects, especially glass fragments, has to be checked. The visible optical domain offers an advantageous alternative solution to the expensive and intrusive x-ray systems. However, such a solution requires the development of robust processing algorithms satisfying real-time industrial constraints, which is a very challenging task. A detection method based on kurtosis and local information that emphasizes connected components is proposed, as well as two robust criteria that give a greater robustness to the detector. A specific kurtosis is calculated using an inclined frame definition that is based on both time and spatial dimensions. Such kurtosis increases the detection capacity of the moving objects and allows the estimation of their direction without adding more costs. The kurtosis being very sensitive to outliers, noisy objects that are very small are filtered, allowing efficient detection of foreign objects, such as glass fragments, as long as they are bigger than the noisy objects. In case of big foreign objects, the low sensitivity of the kurtosis is compensated for by the large detected surface. The proposed detection method can be directly applied on video sequences acquired by a standard RGB camera in industrial environments. The experimental results show the effectiveness of the method in detecting real random foreign objects, regardless of their size or their transparency, in various semiopaque bottles.

A Robust Algorithm for Emoji Detection in Smartphone Screenshot Images

The increasing use of smartphones and social media apps for communication results in a massive number of screenshot images. These images enrich the written language through text and emojis. In this regard, several studies in the image analysis field have considered text. However, they ignored the use of emojis. In this study, a robust two-stage algorithm for detecting emojis in screenshot images is proposed. The first stage localizes the regions of candidate emojis by using the proposed RGB-channel analysis method followed by a connected component method with a set of proposed rules. In the second verification stage, each of the emojis and non-emojis are classified by using proposed features with a decision tree classifier. Experiments were conducted to evaluate each stage independently and assess the performance of the proposed algorithm completely by using a self-collected dataset. The results showed that the proposed RGB-channel analysis method achieved better performance than the Niblack and Sauvola methods. Moreover, the proposed feature extraction method with decision tree classifier achieved more satisfactory performance than the LBP feature extraction method with all Bayesian network, perceptron neural network, and decision table rules. Overall, the proposed algorithm exhibited high efficiency in detecting emojis in screenshot images.

Unconstrained Handwritten Text Line Segmentation for Kannada Language

Segmentation is division of something into smaller parts and one of the Component of character recognition system. Separation of characters, words and lines are done in Segmentation from text documents. character recognition is a process which allows computers to recognize written or printed characters such as numbers or letters and to change them into a form that the computer can use. the accuracy of OCR system is done by taking the output of an OCR run for an image and comparing it to the original version of the same text. The main aim of this paper is to find out the various text line segmentations are Projection profiles, Weighted Bucket Method. Proposed method is horizontal projection profile and connected component method on Handwritten Kannada language. These methods are used for experimentation and finally comparing their accuracy and results.

A Comprehensive Framework for OCR Web Services System for Arabic Calligraphy Documents

This paper describes document layout analysis web services approach for OCR systems, in case of integrate with web-based applications using SOAP and REST interfaces. The proposed solution provides accessing way to use different OCR systems. Therefore, these web services are implemented using SOAP and REST interfaces through HTTP or HTTPS requests. Consequently, different developers can communicate with each other’s without time consuming to customize code implementation, operating system barriers, and programming language conditions. The scientific scope of this paper focuses on three objectives:(1)  The document categories on which they are included in the dataset, (2) The related algorithms that are used in the level of document analysis, and (3) The Arabic document image segmentation algorithms they are used. Consequently, the connected components method is used to remove page frame in the old and calligraphy documents. Also, shadow noises in the old and historical documents are removed using the adapted sparse algorithm.This paper discusses a number of the major areas where OCR web services have been working comprehensively: in supporting document analysis and OCR service-oriented architecture computing. Using the OCR web services approaches, we are dealing with heterogeneous large scale documents with wide varying structured category. Furthermore, there could be multipage document with different languages. Accordingly, the language domain will be identified within the language script specification module.Â

Accurate iris center localization method using facial landmark, snakuscule, circle fitting and binary connected component

Iris centers have been widely used in machine vision for face matching, gaze estimation, etc. However, in low resolution eye images, the iris and its surrounding region present a variety of appearance characteristics, which make it difficult to accurately locate the iris center. In this paper, we propose a robust, accurate and real-time iris center localization method by combining the facial landmark, snakuscule, circle fitting and binary connected component. Facial landmarks are used to extract an accurate eye Region of Interest (ROI). Thereafter, a fixed size circle-based active contour snakuscule is used to detect the iris center. Based on the snakuscule center and inner radius, a novel method is proposed to extract accurate iris edges for circle fitting. In addition, the quality of the detected iris center is evaluated by a circle-binary quality evaluation method. Binary connected component method is used to improve the accuracies in those unqualified images. The proposed method is tested on three publicly available databases BioID, GI4E and Talking Face Video. The result shows that it could achieve an accuracy of 94.35% on the BioID database when the normalized error is smaller than 0.05, which outperforms all state-of-the-art methods.

A physiognomy based method for facial feature extraction and recognition

This paper proposes a novel calculation method of personality based on Chinese physiognomy. The proposed solution combines ancient and modern physiognomy to understand the relationship between personality and facial features and to model a baseline to shape facial features. We compute a histogram of image by searching for threshold values to create a binary image in an adaptive way. The two-pass connected component method indicates the feature's region. We encode the binary image to remove the noise point, so that the new connected image can provide a better result. According to our analysis of contours, we can locate facial features and classify them by means of a calculation method. The number of clusters is decided by a model and the facial feature contours are classified by using the k-means method. The validity of our method was tested on a face database and demonstrated by a comparative experiment.

Localizing seizure onset zone by convolutional transfer entropy from iEEG.

Automatic localization of the seizure onset zone (SOZ) is able to output an objective result and help clinical doctors greatly in epilepsy therapy. Transfer entropy is one of the most frequently used measures based on information theory to localize the SOZ. However, if only using transfer entropy to localize the SOZ, different results can be obtained during different periods, thus humans still need to identify which one is most reasonable. This paper proposes a new method to output only a few (e.g. 1 or 2) results along a long time slot. Based on the results of traditional transfer entropy, we use a 3D convolution method to enhance the connection between the spatial channels and also between different temporal positions. After that, a connected component method is used to extract the stable blocks that indicate the SOZ. To evaluate the effectiveness of our method, preliminary experiments on a short iEEG signals are conducted. The experimental results show that our method can achieve a sensitivity of 100% and a false positive rate of 1.79% for SOZ localization.

Functional Brain Networks: Does the Choice of Dependency Estimator and Binarization Method Matter?

The human brain can be modelled as a complex networked structure with brain regions as individual nodes and their anatomical/functional links as edges. Functional brain networks are constructed by first extracting weighted connectivity matrices, and then binarizing them to minimize the noise level. Different methods have been used to estimate the dependency values between the nodes and to obtain a binary network from a weighted connectivity matrix. In this work we study topological properties of EEG-based functional networks in Alzheimer’s Disease (AD). To estimate the connectivity strength between two time series, we use Pearson correlation, coherence, phase order parameter and synchronization likelihood. In order to binarize the weighted connectivity matrices, we use Minimum Spanning Tree (MST), Minimum Connected Component (MCC), uniform threshold and density-preserving methods. We find that the detected AD-related abnormalities highly depend on the methods used for dependency estimation and binarization. Topological properties of networks constructed using coherence method and MCC binarization show more significant differences between AD and healthy subjects than the other methods. These results might explain contradictory results reported in the literature for network properties specific to AD symptoms. The analysis method should be seriously taken into account in the interpretation of network-based analysis of brain signals.

Feature based Text Extraction System using Connected Component Method

Text detection and segmentation system serves as important method for document analysis as it helps in many content based image analysis tasks. This research paper proposes a connected component technique for text extraction and character segmentation using maximally stable extremal regions (MSERs) for text line formation followed by connected components to determined separate characters. The system uses a cluster size of five which is selected by experimental evaluation for identifying characters. Sobel edge detector is used as it reduces the execution time but at the same time maintains quality of the results. The algorithm is tested along a set of JPEG, PNG and BMP images over varying features like font size, style, colour, background colour and text variation. Further the CPU time in execution of the algorithm with three different edge detectors namely prewitt, sobel and canny is observed. Text identification using MSER gave very good results whereas character segmentation gave on average 94.572% accuracy for the various test cases considered for this study.

An Indoor Obstacle Detection System Using Depth Information and Region Growth

This study proposes an obstacle detection method that uses depth information to allow the visually impaired to avoid obstacles when they move in an unfamiliar environment. The system is composed of three parts: scene detection, obstacle detection and a vocal announcement. This study proposes a new method to remove the ground plane that overcomes the over-segmentation problem. This system addresses the over-segmentation problem by removing the edge and the initial seed position problem for the region growth method using the Connected Component Method (CCM). This system can detect static and dynamic obstacles. The system is simple, robust and efficient. The experimental results show that the proposed system is both robust and convenient.

Defocus noise suppression with combined frame difference and connected component methods in optical scanning holography.

Random phase masks can transform the defocus noise into a speckle-like pattern in optical scanning holography (OSH). In this Letter, we presented a speckle reduction based on combined frame difference and connected component method in a random phase-coded OSH system. The image quality of the reconstructed sections is improved with better visibility.

Segmentation, Separation and Pose Estimation of Prostate Brachytherapy Seeds in CT Images.

In this paper, we address the development of an automatic approach for the computation of pose information (position + orientation) of prostate brachytherapy loose seeds from 3-D CT images. From an initial detection of a set of seed candidates in CT images using a threshold and connected component method, the orientation of each individual seed is estimated by using the principal components analysis method. The main originality of this approach is the ability to classify the detected objects based on a priori intensity and volume information and to separate groups of closely spaced seeds using three competing clustering methods: the standard and a modified k-means method and a Gaussian mixture model with an expectation-maximization algorithm. Experiments were carried out on a series of CT images of two phantoms and patients. The fourteen patients correspond to a total of 1063 implanted seeds. Detections are compared to manual segmentation and to related work in terms of detection performance and calculation time. This automatic method has proved to be accurate and fast including the ability to separate groups of seeds in a reliable way and to determine the orientation of each seed. Such a method is mandatory to be able to compute precisely the real dose delivered to the patient postoperatively instead of assuming the alignment of seeds along the theoretical insertion direction of the brachytherapy needles.

A vascular network matching in dynamic thermography for breast cancer detection

Because of limitation of human visual system, computer-aided diagnosis has been playing an important role in early breast cancer detection. Clinical interpretation of dynamic breast thermograms first depends on the similarity analysis between vascular pattern in thermal images before and after applying a cold challenge. To analyse the thermal images for cancer detection purposes in dynamic breast thermography, a new approach is proposed. First, the breast region was delineated from the background using a connected component method. Then, the blood vessels presented on the segmented breast region were extracted using image morphology. The branching points of the skeletonised vascular network are referred to as thermal minutia points (TMPs). Similar to fingerprints, these feature points are used as a geometric representation of the shape of vein patterns during the classification stage. Local and global structures of TMPs which are extracted from a cold-challenged image are matched with those of baseline image. The experimental results showed that the algorithm reaches 86% of the sensitivity and 61% specificity from 50 thermograms (25 normal and 25 cancerous). The mean of matching scores in malignant and benign cases are 0.78 and 0.3, respectively. According to the results the proposed approach is promising for detection of breast abnormality. More importantly, the results indicated the possibility of this framework in breast cancer detection so as to open a proper way for further methodological and experimental research in this area.