V. K. Govindan

Character recognition—a review

The machine replication of human reading has been the subject of intensive research for more than three decades. A large number of research papers and reports have already been published on this topic. Many commercial establishments have manufactured recognizers of varying capabilities. Handheld, desk-top, medium-size and large systems costing as high as half a million dollars are available, and are in use for various applications. However, the ultimate goal of developing a reading machine having the same reading capabilities of humans still remains unachieved. So, there still is a great gap between human reading and machine reading capabilities, and a great amount of further effort is required to narrow-down this gap, if not bridge it. This review is organized into six major sections covering a general overview (an introduction), applications of character recognition techniques, methodologies in character recognition, research work in character recognition, some practical OCRs and the conclusions.

A pattern adaptive thinning algorithm

A simple sequential thinning algorithm for peeling off pixels along contours is described. An adaptive algorithm obtained by incorporating shape adaptivity into this sequential process is also given. The distortions in the skeleton at the right-angle and acute-angle corners are minimized in the adaptive algorithm. The asymmetry of the skeleton, which is a characteristic of sequential algorithm, and is due to the presence of T-corners in some of the even-thickness pattern is eliminated. The performance (in terms of time requirements and shape preservation) is compared with that of a modern thinning algorithm.

Computer-Aided Identification of the Pectoral Muscle in Digitized Mammograms

Mammograms are X-ray images of human breast which are normally used to detect breast cancer. The presence of pectoral muscle in mammograms may disturb the detection of breast cancer as the pectoral muscle and mammographic parenchyma appear similar. So, the suppression or exclusion of the pectoral muscle from the mammograms is demanded for computer-aided analysis which requires the identification of the pectoral muscle. The main objective of this study is to propose an automated method to efficiently identify the pectoral muscle in medio-lateral oblique-view mammograms. This method uses a proposed graph cut-based image segmentation technique for identifying the pectoral muscle edge. The identified pectoral muscle edge is found to be ragged. Hence, the pectoral muscle is smoothly represented using Bezier curve which uses the control points obtained from the pectoral muscle edge. The proposed work was tested on a public dataset of medio-lateral oblique-view mammograms obtained from mammographic image analysis society database, and its performance was compared with the state-of-the-art methods reported in the literature. The mean false positive and false negative rates of the proposed method over randomly chosen 84 mammograms were calculated, respectively, as 0.64% and 5.58%. Also, with respect to the number of results with small error, the proposed method out performs existing methods. These results indicate that the proposed method can be used to accurately identify the pectoral muscle on medio-lateral oblique view mammograms.

Pectoral muscle identification in mammograms.

In most of the approaches of computer‐aided detection of breast cancer, one of the preprocessing steps applied to the mammogram is the removal/suppression of pectoral muscle, as its presence within the mammogram may adversely affect the outcome of cancer detection processes. Through this study, we propose an efficient automatic method using the watershed transformation for identifying the pectoral muscle in mediolateral oblique view mammograms. The watershed transformation of the mammogram shows interesting properties that include the appearance of a unique watershed line corresponding to the pectoral muscle edge. In addition to this, it is observed that the pectoral muscle region is oversegmented due to the existence of several catchment basins within the pectoral muscle. Hence, a suitable merging algorithm is proposed to combine the appropriate catchment basins to obtain the correct pectoral muscle region. A total of 84 mammograms from the mammographic image analysis database were used to validate this approach. The mean false positive and mean false negative rates, obtained by comparing the results of the proposed approach with manually‐identified (ground truth) pectoral muscle boundaries, respectively, were 0.85% and 4.88%. A comparison of the results of the proposed method with related state‐of‐the‐art methods shows that the performance of the proposed approach is better than the existing methods in terms of the mean false negative rate. Using Hausdorff distance metric, the comparison of the results of the proposed method with ground truth shows low Hausdorff distances, the mean and standard deviation being 3.85±1.07 mm. PACS numbers: 87.57.R, 87.57.nm, 87.59.ej, 87.85.Ng, 87.85.Pq

Shadow Detection and Removal from a Single Image Using LAB Color Space

Abstract A shadow appears on an area when the light from a source cannot reach the area due to obstruction by an object. The shadows are sometimes helpful for providing useful information about objects. However, they cause problems in computer vision applications, such as segmentation, object detection and object counting. Thus shadow detection and removal is a pre-processing task in many computer vision applications. This paper proposes a simple method to detect and remove shadows from a single RGB image. A shadow detection method is selected on the basis of the mean value of RGB image in A and B planes of LAB equivalent of the image. The shadow removal is done by multiplying the shadow region by a constant. Shadow edge correction is done to reduce the errors due to diffusion in the shadow boundary.

Improving BTC image compression using a fuzzy complement edge operator

A simple and easy to implement technique for improving block truncation coding (BTC) is proposed. The method is based on replacement of bit block obtained using the conventional BTC method with the fuzzy logical bit block (LBB) such that the sample mean and standard deviation in each image block are preserved. This fuzzy LBB is obtained from the fuzzy edge image by using the Yager involutive fuzzy complement edge operator (YIFCEO). The input image is encoded with the block mean and standard deviation and the fuzzy LBB. Experimental results show an improvement of visual quality of reconstructed images and peak signal-to-noise ratio (PSNR) when compared to the conventional BTC. The raggedness and jagged appearance and the ringing artifacts at sharp edges are greatly reduced in the reconstructed images. With the use of YIFCEO, the proposed method is shown to be more flexible to determine the visual quality of the reconstructed images.

Palmprint authentication using fusion of wavelet based representations

Wavelets are widely used to extract the texture features for pattern recognition applications including biometric authentication. This can be attributed to the discriminating capability of wavelet features and the availability of fast algorithms for implementing discrete wavelet transform (DWT). In most of the wavelet based palmprint applications, distribution of energies in space-frequency domain are treated as features to classify the palmprints. Although wavelet energies are good discriminating features, they fail to characterize the palmprints sufficiently. In order to enhance the discriminating capability and the palmprint recognition accuracy, we extract the intramodal palmprint line and energy features from the same wavelet decomposition of palmprint. The score level (product rule and sum rule) fusion of these features improves the recognition accuracy significantly. We empirically found 39.38% relative improvement (RI) with an overall equal error rate (EER) of 1.37%, on PolyU online palmprint database (left hand palmprints). The computational burden on feature extraction is very less, and the EER is superior to other state of the art approaches. The comparison of the results with the state of the art wavelet and fusion based palmprint recognition approaches demonstrates the effectiveness of the proposed approach in classifying palmprints.

Agent based dynamic resource allocation on federated clouds

Current large distributed system allows users to share and trade resources. In cloud computing, users purchase different resources like network bandwidth, computing power and storage system from one or more cloud providers for a limited period of time with a variable or fixed price. Federated cloud is a mechanism for sharing resources thereby increasing scalability. Allocating resources in cloud is a complex procedure. In order to improve resource allocation agent based resource allocation method is used. In this method, the user needs not know who is the cloud service provider and where the resources reside. The consumer gets the resources with the minimum price. The proposed system has three types of agents namely Consumer agent, Resource Brokering agent and Resource Provider agent.

Nonlocal-means image denoising technique using robust M-estimator

Edge preserved smoothing techniques have gained importance for the purpose of image processing applications. A good edge preserving filter is given by nonlocal-means filter rather than any other linear model based approaches. This paper explores a different approach of nonlocal-means filter by using robust M-estimator function rather than the exponential function for its weight calculation. Here the filter output at each pixel is the weighted average of pixels with surrounding neighborhoods using the chosen robust M-estimator function. The main direction of this paper is to identify the best robust M-estimator function for nonlocal-means denoising algorithm. In order to speed up the computation, a new patch classification method is followed to eliminate the uncorrelated patches from the weighted averaging process. This patch classification approach compares favorably to existing techniques in respect of quality versus computational time. Validations using standard test images and brain atlas images have been analyzed and the results were compared with the other known methods. It is seen that there is reason to believe that the proposed refined technique has some notable points.

A Fuzzy Complement Edge Operator

A fuzzy complement edge operator has been developed based on the Yager involutive fuzzy complements. The proposed edge operator is validated with a recently available fuzzy edge operator on the basis of the results of the well-known Canny edge operator. The edge operator has been tested with test images of size 256x256 and found to be superior with larger values of edge pixels and better visual quality in edge images.