Narrow Results

Linear Quadtree (LQ), Interpolation-Based Binary tree (IBB) and Minimized Boolean Function (MBF) are some of the set-of-codes type of encoding scheme for region representation of binary images. Chain Code (CC) is a well-known technique for boundary representation of such images. It is desirable to develop efficient methods of conversion between the two types of representation schemes. In this paper, we present a generalized algorithm for conversion from set-of-codes type of representation to chain codes. The computational complexity of the algorithm is also discussed.

This paper presents a real-time constraint-free handprinted character recognition system based on a structural approach. After the preprocessing operation, a chain code is extracted to represent the character. The classification is based on the use of a processor dedicated to string comparison. The average computation time to recognize a character is about 0.07 seconds. During the learning step, the user can define any set of characters or symbols to be recognized by the system. Thus there are no constraints on the handprinting. The experimental tests show a high degree of accuracy (96%) for writer-dependent applications. Comparisons with other system and methods are discussed. We also present a comparison between the processor used in this system and the Wagner and Fischer algorithm. Finally, we describe some applications of the system.

A polygonal approximation captures the essential features of a digital planar curve and yields a compact representation. Those points of the digital curve that carry vital information about the shape of the curve form the vertices of the approximating polygon and are called significant vertices. In this paper, we present a genetic algorithm-based approach to locate a specified number of significant points, such that the approximation error between the original curve and its polygonal version obtained by joining the adjacent significant points is minimized. By using a priori knowledge about the shape of the curve we confine our search to only those points of the curve that have the potential of qualifying as significant points. We also incorporate chromosome differentiation to improve upon the effectiveness of the search in arriving at a near-optimal polygonal approximation. Finally, we show that the proposed method performs remarkably well when evaluated in terms of the metrics available for assessing the goodness of a polygonal approximation algorithm.

A novel algorithm to detect circular arcs from a digital image is proposed. The algorithm is based on discrete curvature estimated for the constituent points of digital curve segments, followed by a fast geometric analysis. The curvature information is used in the initial stage to find the potentially circular segments. In the final stage, the circular arcs are merged and maximized in length using the radius and center information of the potentially circular segments. Triplets of longer segments are given higher priorities; doublets and singleton arcs are processed at the end. Detailed experimental results on benchmark datasets demonstrate its efficiency and robustness.

In this paper, we introduce an efficient method for segmenting the bone region of an X-ray image from its surrounding muscles and tissues. Automated segmentation of the bone part in a digital X-ray image is a challenging problem because of its low contrast with the surrounding flesh. The presence of noise and spurious edges further complicates the segmentation. Most of the existing methods either suffer from noisy contour detection or need training samples for manual tuning of certain thresholding parameters. We propose a fully automated segmentation technique, which utilizes a variant of entropy measure of the image. This scheme has been shown to be useful for fast and efficient analysis of a wide class of human X-ray images including skull, chest, pelvic region and ortho-dental zones. In order to quantify the quality of segmentation, we propose a new metric called average contour distortion index (ACDI) based on certain neighborhood properties of the contour pixels. Experiments on several X-ray images reveal encouraging results compared to other approaches as evident from the ACDI metric. We also re-validate the quality of several segmented bone images using segmentation entropy quantitative assessment (SEQA), and boundary-based precision–recall profile. All three metrics establish the superiority of the proposed technique to prior art.

This paper presents a comparative analysis of segmentation and non-segmentation based techniques for cursive handwritten word recognition. In our segmentation based technique, every word is segmented into characters, the chain code features are extracted from segmented characters, the features are fed to neural network classifier and finally the words are constructed using a string compare algorithm. In our non-segmentation based technique, the chain code features are extracted directly from words and the words are fed to a neural network classifier to classify them into word classes. To make a fair comparison, a CEDAR benchmark database is used, and the parameters such as the number of words, thresholding, resizing, feature extraction techniques, etc. are kept same for both the techniques. The experimental results and analysis show that the non-segmentation technique achieves higher recognition rate than the segmentation based technique.

This paper presents a real-time constraint-free handprinted character recognition system based on a structural approach. After the preprocessing operation, a chain code is extracted to represent the character. The classification is based on the use of a processor dedicated to string comparison. The average computation time to recognize a character is about 0.07 seconds. During the learning step, the user can define any set of characters or symbols to be recognized by the system. Thus there are no constraints on the handprinting. The experimental tests show a high degree of accuracy (96%) for writer-dependent applications. Comparisons with other systems and methods are discussed. We also present a comparison between the processor used in this system and the Wagner and Fischer algorithm. Finally, we describe some applications of the system.