Efficient and robust detection and recognition of objects in grayscale images.

A new method for the detection and recognition of objects was developed for grayscale images. Obstacle detection is achieved by an efficient segmentation method and a labelling algorithm. This segmentation methodology is based on an efficient binarization and enhancement techniques followed by a suitable connected component analysis procedure. Image binarization successfully processes images having shadows, non- uniform illumination and low contrast. The grayscale object corresponding to the object identified in the binary image is then extracted. The second step deals with the recognition of these extracted objects. Each object is then described by Zernike moments. To achieve rotation and scaling invariance an efficient method based on bounding box is used. In order to achieve better results for object recognition, the architecture of Support Vector Machine classifiers utilizing decision tree for solving multiclass problems is used. The algorithm performs the task of object detection and recognition more efficiently, even with external constraints i.e. image scenes can have shadows, partial occlusion and non- uniform illumination and at a much faster rate. The efficiency of the proposed method on grayscale images is shown by cascading some objects from COIL -8 database.

Conference information: 2010 IEEE International Conference on Computational Intelligence and Computing Research held on
28th & 29th Dec 2010 in Tamilnadu, India.