Search

Image compression is process to remove the redundant information from the image so that only essential information can be stored to reduce the storage size, transmission bandwidth and transmission time. The essential information is extracted by various transforms techniques such that it can be reconstructed without losing quality and information of the image. In this research comparative analysis of image compression is done by four transform method, which are Discrete Cosine Transform (DCT), Discrete Wavelet Transform( DWT) & Hybrid (DCT+DWT) Transform and fractal coding. MATLAB programs were written for each of the above method and concluded based on the results obtained that hybrid DWT-DCT algorithm performs much better than the standalone JPEG-based DCT, DWT algorithms in terms of peak signal to noise ratio (PSNR), as well as visual perception at higher compression ratio. The popular JPEG standard is widely used in digital cameras and web based image delivery. The wavelet transform, which is part of the new JPEG 2000 standard, claims to minimize some of the visually distracting artifacts that can appear in JPEG images. For one thing, it uses much larger blocks- selectable, but typically 1024 x 1024 pixels for compression, rather than the 8 X 8 pixel blocks used in the original JPEG method, which often produced visible boundaries. Fractal compression has also shown promise and claims to be able to enlarge images by inserting realistic detail beyond the resolution limit of the original.

Objectives: The main objective is the development of an efficient method in the recognition of vehicles in real world. Methods: The system relies on setting up of an alternate direct SVM classifier for every model in the planning set. Each of these Exemplar-SVMs is subsequently defined by a singular positive event and a large number negatives. While each discoverer is altogether specific to its model, we precisely watch that a troupe of such Exemplar-SVMs offers shockingly awesome theory. Our execution on the PASCAL VOC revelation errand is keeping pace with the altogether all the more bewildering idle part-based model of Felzenszwalb et al., at only a humble computational cost increase. But the central benefit of our approach is that it makes an unequivocal relationship between each acknowledgment and a singular get ready model. Findings: Since most revelations show incredible course of action to their related model, it is possible to trade any open model meta-data (segmentation, geometric structure, 3D model, etc.) clearly onto the recognizable pieces of proof, which can then be used as an element of general scene understanding. The current methods are taking negative information and processing them. They use the information mining to filter out the negative values, since the classifier is direct SVM the values are represented parametrically. However this system depends on an exceptionally basic thought. We use every model utilizing unending HOG template. The use of exemplar SVM will make the number of examples in the dataset more and the efficient way of processing the objects and identifying them. Applications: This system can be used for Indian roads scenario since there is no proper lane marking system and there is always a chance to get many disturbances in the images. This system can be more developed into a constant evolving model where the processed objects can be stored within and keeps on integrating the data set.