Department of Computer Science & Engineering

&ldquo;IIT Jodhpur is committed to impart quality education to facilitate the creation of qualified, competent and responsible human resources to meet the emerging technological challenges of the world. It is working towards creating an equitable learning platform that is positive, accessible and effective in the face of the modern societal and scientific advancements.

Flexibility in curriculum, in all its academic programs, encompassing elements of teaching, research, creativity, innovation and entrepreneurship is the most unique feature of IIT Jodhpur. The Department of Science and Technology (DST), under the National Mission on Cyber Physical Systems, has identified IIT Jodhpur as a Technology &amp; Innovation Hub in the area of Augmented Reality and Virtual Reality. The institute has also been nominated as the coordinator for the Jodhpur City and Knowledge Cluster by the Office of Principal Scientific Adviser, Government of India.

The sprawling 852-acre IIT Jodhpur campus is a majestic tribute to the deep-rooted diverse cultural heritage of the region. The campus is an architectural masterpiece, which is slated to become an international exemplar of sustainability with net-zero energy, and advanced water and waste management strategies.&rdquo;

IIT Jodhpur

In this paper, a technique is presented for obtaining polygonal approximation of object contours directly from the edge images. The technique is based on a new formulation of Hough transform (HT) for aggregation of edge points into line segments. The space requirement of the HT is brought down by considering a different parameterization of straight lines. In this method, the process of edge linking and boundary approximation are combined into a single algorithm. Consequently, the scheme is computationally more efficient than the classical boundary approximation techniques which require use of a separate edge linking algorithm for obtaining linked list of edge points as their input. Experimental results presented here highlight the effectiveness of this method for approximating object boundaries of polygonal as well as curved shapes present in the images of complex multi-object scenes. © 1992 IEEE.

World University root node

Proceedings - International Conference on Pattern Recognition

A hough transform based approach to polyline approximation of object boundaries

A connectionist network has been presented here for simultaneous perception of multiple categories. These categories provide an adequate explanation of the input features originating from multiple classes. The network optimises an appropriately defined error function for making the inference. A supervised learning algorithm is presented for learning the association between the features and each individual category. © 1992 Institute of Electrical and Electronics Engineers Inc. All rights reserved.

A connectionist network for simultaneous perception of multiple categories

This paper addresses various aspects of the problems associated with processing and recognition of printed and handwritten Bengali numerals. A scheme has been proposed for recognizing handwritten as well as printed numerals with different fonts and writing styles. The scheme was successfully used for the recognition of the writer from samples of handwritten numerals and the font from printed numerals with a high degree of accuracy. The scheme was also extended for noisy and occluded numerals. The standard multi-layer perceptron (MLP) augmented with MAXNET was used as a classifier. The experiments presented have established the superiority of the MLP and MAXNET combine over the standard MLP classifier and the classical nearest neighbour classifier. © 1992 IEEE.

Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

On recognition of Bengali numerals with back propagation learning

In this paper a connectionist clustering strategy is presented for segmenting color images. First the local peaks in the 3-D R,G,B histogram are located. Then using these as the prototypes other patterns are classified to one of them. The prototype selection and classification networks have been analyzed. The prototype selection method employs only neuronal dynamics and therefore is faster than existing clustering neural networks. The classification network takes into account the distribution of the data and hence is less prone to misclassifications. Experimental results obtained by applying the network for segmenting one color image is presented. © 1992 IEEE.

A connectionist approach for color image segmentation

Peak detection in multidimensional parameter space is an important aspect of feature detection using the Hough transform. In this paper a connectionist network is presented for detecting peaks in multidimensional Hough space. The neural network implementation successfully uses circumstantial evidence and detects multiple winners over the parameter space such that these winners correspond to parameters of features in the image. The dynamics of the network has been analysed and the conditions for convergence have been established. Experimental results obtained by applying the network for detecting straight lines in three images are presented. The results obtained are promising. © 1992.

Pattern Recognition

A connectionist approach for peak detection in Hough space

In this paper a connectionist network is presented for segmenting gray level images. The network detects the local peaks in the inverted histogram which will correspond to the bottoms of the valleys in the actual histogram. The neural network implementation successfully uses circumstantial evidence and detects multiple winners over the entire range of gray values such that these winners correspond to multiple thresholds for segmenting the image. The dynamics of the network has been analyzed and and the conditions for convergence have been established. Experimental results obtained by applying the network for segmenting two X-ray images are presented. The results obtained are promising. © 1992 IEEE.

A connectionist approach for gray level image segmentation

The problem of detecting correspondences between object contours belonging to successive image frames of a dynamic scene is addressed. The object contours are represented using concave, convex and straight line segments which are extracted after smoothing the contour with a Gaussian kernel. The matching problem is tackled using heuristic search with a state space formulation. An admissible heuristic function is designed for guiding the search. Experimental results are presented to demonstrate the capabilities of the method.

IEE Proceedings E: Computers and Digital Techniques

Heuristic search approach to shape matching in image sequences

Reactions of steroidal epoxides such as 5,6$\alpha$-epoxy-5$\alpha$-cholestane (I) and its 3$\beta$-chloro (H) and 3$\beta$-acetoxy (III) analogs with urea in dimethylformamide afforded 6$\beta$-amino-5$\alpha$-cholestan-5-ol (IV-VI), 6$\beta$-amino-N-formyl-5$\alpha$-cholestan-5-ol (VII-IX) and 6$\beta$-amino-N-amido-5$\alpha$-cholestan-5-ol (X-XII), along with the 5$\alpha$-cholestane-5,6$\beta$-diol (XIII-XV). In addition to these compounds, the 3$\beta$-acetoxy analog also afforded the N-carboxyl derivative (XVI). {\textcopyright} 1990.

Steroids

Synthesis of aminosterols and their derivatives

This paper presents a new heuristic search based approach for recognition of partially obscured planar shapes. Based on a general scheme for representing the planar shapes in terms of their contour segments, a state space formulation is obtained for the recognition problem. The search in the state space is guided by an admissible heuristic function which is not dependent upon the features actually used for representing the shapes. Some schemes for toning up the efficiency of the method are also discussed. A study of the method was carried out by experimenting with some typical objects and results of experimentation are presented. © 1990.