Computer Vision Research Group


Vehicle make and model recognition system is now an integral part of public access control systems installed at parking lots, buildings and streets for implementing security measures. They also enhance the capability of automatic number plate recognition systems for monitoring traffic on highways. To recognize the make and model of car in real environments the proposed approach should be able to demonstrate its classification results on a dataset of car images with minimum controlled conditions and contain a large number of vehicle types. read detail


Download read_dirr.m


Text data present in images and videos provide highly useful information for understanding image content, automatic annotation, indexing, and structuring of images and videos. Currently no public database is available to serve training and testing purpose in text related applications. We have compiled a challenging dataset termed as: COMVis Text Dataset 2010 "CVTD 2010". The dataset contains more than 2000 text and 2200 non-text samples collected from various natural scene still images from web and CCTV videos. Text samples with different font-styles, sizes, colours, directions, various text and background contrast combinations, poor quality text, etc. have been included in the dataset. Apart from positive and negative training samples, the dataset contains more than 400 positive and negative test images as well. The main purpose of compiling such a dataset is that it can serve as a training database for text related applications not only for still images but for low resolution real time videos as well because such a dataset did not existed before.


Recent News
© 2010 Department of Electrical Engineering, CIIT Lahore  |  Terms and Conditions