Search

This paper evaluates and compares the performance of K-Nearest Neighbors (KNN), Support Vector Machine (SVM) and Sparse Representation Classifier (SRC) for recognition of isolated Arabic handwritten characters. The proposed framework converts the gray-scale character image to a binary image through Otsu thresholding, and size-normalizes the binary image for feature extraction. Next, we exploit image down-sampling and the histogram of image gradients as features for image classification and apply fusion (combination) of these features to improve the recognition accuracy. The performance of the proposed system is evaluated on Isolated Farsi/Arabic Handwritten Character Database (IFHCDB) – a large dataset containing gray scale character images. Experimental results reveal that the histogram of gradient consistently outperforms down-sampling based features, and the fusion of these two feature sets achieves the best performance. Likewise, SRC and SVM both outperform KNN, with the latter performing the best among the three. Finally, we achieved a commanding accuracy of 93.71% in character recognition with fusion of features classified by SVM, where 92.06% and 91.10% is achieved by SRC and KNN respectively.

Wireless Capsule Endoscopy (WCE) has emerged as a popular non-invasive imaging tool for inspection of human Gastrointestinal (GI) tract. In order to identify the location of an anomaly or intestinal disease, the physicians need to know the exact location of the endoscopic capsule which influences the treatment plan. In this paper, we present a displacement estimation technique based on feature point tracking which utilizes the images captured by a commercial capsule, named PillCam. The proposed displacement calculation approach is tested using a virtual testbed. Results show that, with assistance of ASIFT-RANSAC algorithms, the proposed algorithm is able to estimate the linear displacement of the endoscopic capsule with an accuracy of 93.7% on average.

We present a novel approach for abnormal breast mass classification from digitized mammography images. The proposed framework exploits rotation invariant uniform Local Binary Pattern (LBP) as texture feature. These features are classified using Support Vector Machine (SVM). In addition, we take advantage of the breast mammograms taken from multiple views or angles. We classify breast scans from ‘cranial-caudal’ view and ‘mediolateral-oblique’ view separately, and combine these classification scores to make an improved diagnosis. This reduces the classification error, and achieves higher recognition rate than that of either views individually. The proposed computer aided diagnosis system was evaluated on DDSM (Digital Database for Screening Mammography) data set, and was able to achieve a classification accuracy of 74%.

Local Binary Pattern (LBP) is a simple yet robust texture descriptor that has been widely used in many computer vision applications including face recognition. In this paper, we exploit LBP for handwritten Bangla numeral recognition. We classify Bangla digits from their LBP histograms using K Nearest Neighbors (KNN) classifier. The performance of three different variations of LBP - the basic LBP, the uniform LBP and the simplified LBP was investigated. The proposed OCR system was evaluated on the off-line handwritten Bangla numeral database CMATERdb 3.1.1, and achieved an excellent accuracy of 96:7% character recognition rate.

We present a framework for handwritten Bangla digit recognition using Sparse Representation Classifier. The classifier assumes that a test sample can be represented as a linear combination of the train samples from its native class. Hence, a test sample can be represented using a dictionary constructed from the train samples. The most sparse linear representation of the test sample in terms of this dictionary can be efficiently computed through l 1 -minimization, and can be exploited to classify the test sample. We applied Sparse Representation Classifier on the image zone density, an image domain statistical feature extracted from the character image, to classify the Bangla numerals. This is a novel approach for Bangla Optical Character Recognition, and demonstrates an excellent accuracy of 94% on the off-line handwritten Bangla numeral database CMATERdb 3.1.1. This result is promising, and should be investigated further.

Elastography is a promising technique for detection and classification of abnormal growth and tumors in soft tissues. In this paper we propose a simple yet effective optimization to speed up the time-domain indirect strain estimation. The proposed method exploits the displacement values of the neighbours to predict the displacement and utilizes this predicted value to define an adaptive search region for finding the best match between pre and post compression signals. This Proposed method is faster than other block matching algorithms such as SAD, SSD or cross-correlation. We have evaluated the method using performance parameters such as elastrographic Signal to Noise Ratio (SNRe), elastrographic Contrast to Noise Ratio (CNRe), elastrographic Peak-Signal to Noise Ratio (PSNRe) and Mean Structural Similarity (MSSIM). For lower percentage of strain, the proposed method faster demonstrated similar performance to the other methods.

Cell segmentation in microscopic images is inherently challenging due to the embedded optical artifacts and the overlapping of cells. Proper segmentation can help for shape analysis, motion tracking and cell counting. We present a framework for cell segmentation and counting by detection of cell centroids in microscopic images. The method is specifically designed for counting circular cells with a high probability of occlusion. The proposed algorithm has been implemented and evaluated on images of fluorescent cell population, collected from the Broad Bioimage Benchmark Collection (www.broad.mit.edu/bbbc), with different degrees of overlap probability. The experimental results show an excellent accuracy of 92% for cell counting even at a very high 60% overlap probability.

We present the Adaptive Vector Pattern Matching (AVPM) method, a novel method for the detection of vortical structures specifically designed for velocity encoded 4D PCMRI datasets. AVPM is based on vector pattern matching combined with robust orientation estimation. This combination provides for a simple yet robust algorithm, which is a priori axial flow invariant. We demonstrate these properties by comparing the performance of AVPM with Heiberg's Vector Pattern Matching algorithm.