No abstract

Agro export industries generate a substantial amount of revenue to Indian economy. In the fruit industry, various fruits like banana, mango, apple and pomegranate, etc. are transported in the conveyor for a post harvest process like classification, sorting, grading and juice extraction. The manual discrimination of various fruits consumes time and, it can be automated. This research work is intended to build an image processing algorithm that ensures automatic discrimination of banana (Musa Species.) from other fruits like Citrus, Apple, and Pomegranate. The input object is segmented using Background subtraction and threshold method. Morphological operations are performed to obtain the clear contour of the segmented objects. The shape of the banana and non-banana are described by scale and translation invariant signature. Binary SVM with signature feature vectors detect the banana fruit from the non-banana fruit automatically. The accuracy rate is 95%.

No abstract

No abstract

Problem statement: Multiple cameras are employed for surveillance of larger environment. In such a case there is a need to maintain overlap in the adjacent cameras for correct object registration. Overlap may get disturbed by natural or manual factors. This study proposed an automatic camera pan correction by determining the area of overlap from multi-view images. Approach: A closed loop system which used feature extraction using SIFT, feature matching using descriptor ratio method and Mean Absolute Error (MAE) over Gaussian scale space, followed by overlap estimation is implemented for restoring the camera position. Results: The proposed method was experimented with the datasets acquired in the environment where surveillance involves two cameras. The matched points of the two images were used to calculate the overlap percentage. The overlap percentage estimated by the surveillance server was communicated to the pan controller to re-orient the camera to its original position. Conclusion: The proposed algorithm identified the robust and distinctive features that are invariant to translation, rotation and scaling. These features help in the accurate estimation of overlap percentage, which is further used to automatically correct the pan of the camera