A Review on Improved Ordered Dither Block Truncation Coding Technique by using K-Nearest Neighbor (Knn) and Neural Networks for Content-Based Image Retrieval

Abstract

This paper represents a technique used Content-Based Image Retrieval by exploiting the advantage of low complexity Ordered-Dither Block Truncation Coding for the generation of image content descriptor. Advantage : The ODBTC image compression is on its low complexity in generating bitmap image by incorporating the Look-Up Table (LUT), and free of mathematical multiplication and division operations on the determination of the two extreme quantizers. It will reduce computation time and yield better image quality. Conversely, ODBTC identifies the minimum and maximum values each image block as opposed to the former low and high mean values calculation, which can further reduce the processing time in the encoding stage. ODBTC Encoding Steps: ODBTC encoding is divided into two parts one is a generation of the bitmap image and second is a calculation of minimum quantizer and maximum quantizer. Neural networks can be very useful for image processing applications. In Neural networks re-emerged only after some important theoretical results were attained in the early eighties most notably the discovery of error backpropagationand new hardware developments increased the processing capacities.