Connected Component Extraction Research Articles

Brain Extraction in Multiple T1-weighted Magnetic Resonance Imaging slices using Digital Image Processing techniques

Brain Imaging has been source of several studies in the literature, mostly due to its importanceboth to predict and to analyze certain diseases or conditions. Extracting the brain from patient images for medical analysis can provide useful diagnostic and prognostic information.To this end, digital image processing algorithms have been applied to medical tasks with a focus on the identification of the brain. This work proposes a brain extraction framework based on three major steps: 1) Dataset and Image Selection; 2) Preprocessing; and 3) Largest Connected Component extraction. Our data are obtained from the OASIS dataset.The preprocessing step is applied in order to enhance contrast and eliminate possible noise from the T1-weighted MRI. Largest Connected Component extraction is performed by initially detecting the largest element in the image (i.e. the brain gray matter) and then by extracting it through mathematical morphology operators. The unsupervised framework extracts the brain in different axial slices without adjustments. The main contribution of this work is a method using only digital image processing for automatically identifying the brain from several different slices, which differs from the literature since is performed without parameter resetting. Five metrics were applied to evaluate our results: Specificity, Recall, Accuracy, F-Measure, and Precision. In our first experiment, two metrics resulted in more than 90% in efficiency (Specificity and Precision), two of them surpassed 80% (F-Measure and Accuracy), and Sensitivity exceeded 70%. Our second experiment compares our results with those produced by related works, having been ranked in the top positions of Sensitivity and Specificity.

Writer Identification of Lampung Handwritten Documents Based on Selected Characters

Writer identification is a sub-field in handwriting recognition which its objective is to determine the identity of the writer based on handwriting input. The goal is usually for forensic purposes such as finding the perpetrators of crimes that leave traces of evidence in the form of written messages. In addition, writer identification can also be used to determine the identity of a historical actor if he or she leaves a valuable written artefact. The object of this research is the traditional character of the Lampung region which is so-called Had Lampung by the local community. The traditional character of Lampung consists of 20 main characters and 12 diacritics. Based on selected characters, the writer will be recognized using the Principal Component Analysis (PCA) feature. PCA is one linear feature extraction method of an object in pattern recognition. The PCA algorithm consists of several stages, namely the calculation of the average dataset, the subtraction of the vector dataset with averages, the calculation of covariance, the calculation of eigenvectors and eigenvalues, eigenvector reduction, and the projection of the dataset against reduced eigenvector space. PCA in this paper is used as a feature in image recognition. The dataset utilized in this study is the Lampung Dataset which is a handwritten character recognition (HWCR) dataset. Lampung Dataset consists of 82 Lampung handwritten documents. All Lampung character images in the dataset were extracted from these documents using the connected component extraction algorithm and eventually generated 32,140 images. Furthermore, these images are converted into grayscale images. In this research, as many as 12,500 grayscale images of Lampung handwriting characters were chosen to represent 82 different writers. This data is employed as training and testing data on the proposed method. The highest accuracy of the identification of the writer using this PCA feature is 82.92%, while the lowest accuracy is 28.29%.

Precise Localization of Concealed Objects in Millimeter-Wave Images via Semantic Segmentation

Existing concealed objects detection methods in active millimeter wave (AMMW) images are mainly based on bounding boxes. In this paper, we consider the problem of precise localization of concealed objects in AMMW images with the use of semantic segmentation networks. To improve the performance of the detection and localization of concealed objects, we propose a method with two steps. In the first step, we build a two-class semantic segmentation network to segment concealed objects in pixels from the images with the complex human body background, while in the second step, we use connected components extraction to detect and localize concealed objects in the segmented image. To improve the performance of the detection and localization of small objects, the network we built is composed of stacked dilated convolution blocks to enlarge the receptive field while keeping the resolution of associated feature maps unchanged. In addition, we give a rule for design of the associated dilation rates and the expand-contract dilation (ECD) assignment strategy for the pattern of the dilation rates. In the numerical experiments, we use the universal evaluation metrics, such as the AP (average precision) @ IoU (Intersection over Union)=0.5 and mIoU (mean value of IoU) to evaluate the performance of precise localization. The experiment results show that our method outperforms the existing ones for precise object localization in AMMW images, where the improvement of the AP@0.5 is about 38% and that of the mIoU is about 27%.

Strain gauges position based on machine vision positioning

In this article, in order to meet the requirement of automatic positioning before strain gauge grinding, we proposed a new machine vision algorithm based on connected region extraction and minimum circumferential rotation rectangle delineation. At first, based on the location information of the strain gauge, we used algorithms for image binaryzation, and extracted the strain gauge block by using the connected component extraction method, next roughly positioned strain gauges. And then we dispersed the part which connected to the strain gauge, moreover, found the minimum external rotating rectangle of each strain gauge in the pair of strain gauges so as to located the center of the strain gauge and realize the strain gauge positioning in the end. Then the position of other strain gauge was inferred according to the position of strain gauge in the corner. Experimental verification showed that the error of the algorithm in this article is under 0.05mm, and the algorithm met the requirements of project positioning that the error has to below 0.1mm.

Segment-before-Detect: Vehicle Detection and Classification through Semantic Segmentation of Aerial Images

Like computer vision before, remote sensing has been radically changed by the introduction of deep learning and, more notably, Convolution Neural Networks. Land cover classification, object detection and scene understanding in aerial images rely more and more on deep networks to achieve new state-of-the-art results. Recent architectures such as Fully Convolutional Networks can even produce pixel level annotations for semantic mapping. In this work, we present a deep-learning based segment-before-detect method for segmentation and subsequent detection and classification of several varieties of wheeled vehicles in high resolution remote sensing images. This allows us to investigate object detection and classification on a complex dataset made up of visually similar classes, and to demonstrate the relevance of such a subclass modeling approach. Especially, we want to show that deep learning is also suitable for object-oriented analysis of Earth Observation data as effective object detection can be obtained as a byproduct of accurate semantic segmentation. First, we train a deep fully convolutional network on the ISPRS Potsdam and the NZAM/ONERA Christchurch datasets and show how the learnt semantic maps can be used to extract precise segmentation of vehicles. Then, we show that those maps are accurate enough to perform vehicle detection by simple connected component extraction. This allows us to study the repartition of vehicles in the city. Finally, we train a Convolutional Neural Network to perform vehicle classification on the VEDAI dataset, and transfer its knowledge to classify the individual vehicle instances that we detected.

Natural scene text detection by multi-scale adaptive color clustering and non-text filtering

In recent years, natural scene text detection gains increasing attention because it plays an important role in many computer related techniques. In this paper, we propose a text detection method consisting of two major steps: connected components (CCs) extraction and non-text filtering. For CCs extraction, a multi-scale adaptive color clustering approach is proposed, which can extract text from images in different color complexities and is robust to contrast variation. For non-text filtering, we combine text covariance descriptor (TCD) with histogram of oriented gradients (HOG) to construct feature vectors and use them to distinguish text from background at character and text line levels. Besides, a new text line generation strategy combining both refined and unrefined CCs is applied, which can retrieve some mis-eliminated characters and generate more integrated text lines. Experiments are conducted on two publicly available datasets, the ICDAR 2013 and the ICDAR 2011 datasets, the obtained F-measures on which are 0.76 and 0.75, respectively. Comparative results with some state-of-the-art text detection algorithms demonstrate that the proposed method achieves competitive performance on text detection.

Anti-Forensics of JPEG Images using Interpolation

Segmentation of Arabic text is a major challenge that shall be addressed by any recognition system. The cursive nature of Arabic writing makes it necessary to handle the segmentation issue at various levels. Arabic text line can be viewed as a sequence of words which in turn can be viewed as a sequence of sub-words. Sub-words have the frequently encountered intrinsic property of sharing the same vertical space which makes vertical projection based segmentation technique inefficient. In this paper, the task of segmenting handwritten Arabic text at sub-word level is taken up. The proposed algorithm is based on pulling away the connected components to overcome the impossibility of separating them by vertical projection based approach. Graph theoretic modeling is proposed to solve the problem of connected component extraction. In the sequel, these components are subjected to thorough analysis in order to obtain the constituent sub-words where a sub-word may consist of many components. The proposed algorithm was tested using variety of handwritten Arabic samples taken from different databases and the results obtained are encouraging.

A High Performance Hybrid Technique of Microaneurysm Extraction Using Vessel Suppression and Connected Component Extraction

Detection of microaneurysms in the early stage is a crucial step towards identifying non - proliferative diabetic retinopathy in diabetic patients. Micro aneurysms appear in the form of tiny red dots in fundus images near the blood vessels. Thus making it is very difficult to identify them through ordinary techniques. In this paper we propose a hybrid technique which uses vessel suppression in increase the performance and accuracy of microaneurysms detection. The entire process can be divided into four stages. First the pre-processing stage which enhances the contrast and eliminates noise by contrast limited histogram equalization and bilateral filter respectively. Then multiscale hessian transform based enhancement is performed which includes vessel extraction and suppression. Finally the microaneurysms are extracted using connect component extraction and classified based on features extracted. This technique eliminates the number of false positives detected at every stage thus improving the sensitivity of the system. The algorithm has been thoroughly tested on numerous images and it outperformed the existing counterparts.

Scene text detection using adaptive color reduction, adjacent character model and hybrid verification strategy

Text detection is a primary task for text recognition and understanding, which can be used in many image analysis techniques. In this paper, we propose an effective scene text detection method including three major steps: connected components (CCs) extraction, character-linking and text/non-text classification. First, for CCs extraction, we design an adaptive color reduction scheme by analyzing image color histogram, which reasonably selects color centers and generates unfixed number of color layers for images in different color complexities. Then, for character-linking, an adjacent character model is built by training an extreme learning machine (ELM), instead of setting various thresholds in previous approaches. Finally, a hybrid text verification strategy is adopted, combining convolutional neural network with ELM for text/non-text classification and performing better than just using one of them. Experimental results on some publicly available datasets illustrate the effectiveness of our method and comparative results with some state-of-the-art algorithms demonstrate our competitiveness.

Precise measurement of volume of eccrine sweat gland in mental sweating by optical coherence tomography

We have demonstrated dynamic analysis of the physiological function of eccrine sweat glands underneath skin surface by optical coherence tomography (OCT). In this paper, we propose a method for extraction of the specific eccrine sweat gland by means of the connected component extraction process and the adaptive threshold method, where the en face OCT images are constructed by the swept-source OCT. In the experiment, we demonstrate precise measurement of the volume of the sweat gland in response to the external stimulus.

Topological Concepts Applied to Image Segmentation

This paper presents an automatic method relevant to medical image segmentation of magnetic resonance image with tumors, by means of fuzzy hybrid filter, and connected component extraction. A fuzzy hybrid filtering technique (FH3F) is used to denoise the medical image and the topological concepts are applied to extract connected components and edge detection.

Layout Analysis for Camera-Based Whiteboard Notes

A domain where, even in the era of electronic document processing, hand- writing is still widely used is note-taking on a whiteboard. Such documents are either captured by a pen-tracking device or - which is much more challenging - by a cam- era. In both cases the layout analysis of realistic whiteboard notes is an open research problem. In this paper we propose a camera-based three-stage approach for the automatic lay- out analysis of whiteboard documents. Assuming a reasonable foreground-background separation of the handwriting it starts with a locally adaptive binarization followed by connected component extraction. The latter are then automatically classified as repre- senting either simple graphical elements of a mindmap or elementary text patches. In the final stage the text patches are subject to a clustering procedure in order to gener- ate hypotheses for those image regions where textual annotations of the mindmap can be found. In order to demonstrate the effectiveness of the proposed approach we report results of a writer independent experimental evaluation on a data set of mindmap images created by several different writers without any constraints on writing or drawing style.

Text line detection in handwritten documents

In this paper, we present a new text line detection method for handwritten documents. The proposed technique is based on a strategy that consists of three distinct steps. The first step includes image binarization and enhancement, connected component extraction, partitioning of the connected component domain into three spatial sub-domains and average character height estimation. In the second step, a block-based Hough transform is used for the detection of potential text lines while a third step is used to correct possible splitting, to detect text lines that the previous step did not reveal and, finally, to separate vertically connected characters and assign them to text lines. The performance evaluation of the proposed approach is based on a consistent and concrete evaluation methodology.

Document representation and its application to page decomposition

Transforming a paper document to its electronic version in a form suitable for efficient storage, retrieval, and interpretation continues to be a challenging problem. An efficient representation scheme for document images is necessary to solve this problem. Document representation involves techniques of thresholding, skew detection, geometric layout analysis, and logical layout analysis. The derived representation can then be used in document storage and retrieval. Page segmentation is an important stage in representing document images obtained by scanning journal pages. The performance of a document understanding system greatly depends on the correctness of page segmentation and labeling of different regions such as text, tables, images, drawings, and rulers. We use the traditional bottom-up approach based on the connected component extraction to efficiently implement page segmentation and region identification. A new document model which preserves top-down generation information is proposed based on which a document is logically represented for interactive editing, storage, retrieval, transfer, and logical analysis. Our algorithm has a high accuracy and takes approximately 1.4 seconds on a SGI Indy workstation for model creation, including orientation estimation, segmentation, and labeling (text, table, image, drawing, and ruler) for a 2550/spl times/3300 image of a typical journal page scanned at 300 dpi. This method is applicable to documents from various technical journals and can accommodate moderate amounts of skew and noise.

Address block location on handwritten Korean envelopes by the merging and splitting method

In this paper, we propose a knowledge-based system for locating Destination Address Block (DAB) on handwritten Korean envelopes by the merging and splitting method. In the proposed system, the preprocessing steps such as adaptive binarization, connected component extraction, and deskewing are carried out first. Then, DAB containing address part, name part and zipcode part, of the input envelope image is extracted by an iterative procedure based on the knowledge acquired from the statistical feature analysis of the various handwritten Korean envelopes. Most of the systems for locating address blocks on the envelopes extracted DAB by segmenting an envelope image into several candidate blocks followed by selecting one among the candidate blocks. Because it is very difficult to segment a handwritten Korean envelope image into several blocks, due to the specific writing habits that the addresses on the envelope are written in close proximity to each other, the proposed iterative procedure determines DAB by merging and splitting the connected components, and verifies the determined DAB without segmentation and selection. Experiments with a great number of live handwritten Korean envelopes provided from Seoul Mail Center in Korea were carried out. Experimental results reveal that the proposed system is very effective for address block location on handwritten Korean envelopes.