2 results
Search Results
Now showing 1 - 2 of 2
Conference Object Face Detection Algorithm With Facial Feature Extraction for Face Recognition System(Mechatronics and Machine Vision in Practice, 2013) Gürel,C.; Erden,A.A face recognition system is one of the biometric information processes, its applicability is easier and working range is wider than other systems like; fingerprint, iris scanning, signature, etc. The detection methods are designed to extract features of face region out of a digital image. The output face image of the detection algorithm should be similar to the recognition input image. Face detection is performed on live acquired images without any application field in mind. The developed system uses white balance correction, skin like region segmentation, facial feature extraction and face image extraction on a face candidate. System is also capable of detecting multiple faces in live acquired images.Conference Object Rose Stem Branch Point Detection and Cutting Point Location for Rose Harvesting Robot(Mechatronics and Machine Vision in Practice, 2015) Gürel,C.; Hassan,M.; Zadeh,G.; Erden,A.The primary objective of the study is to develop a method that can locate the proper location of cutting point of rose stem for robotic rose harvesting. Stem tracking and cutting operation are achieved using with the help of stereo vision techniques. The cutting point has a vital importance for cut rose harvesting in greenhouse which affects the efficiency of new shoot from the cut stem. In agricultural process, the cutting point depends on thickness of stem and eye on stem. Locating the eye is difficult by image processing thus another relation for cut point estimation was performed. The relation between thickness and cut length can lead to relation for cut point estimation. 239 data is collected from a greenhouse and linear relation with some deviation was acquired. To perform this relation, branch point location algorithm was developed. The proposed algorithm has three steps: branch point detection; thickness calculation; and cutting length estimation. The algorithm for branch detection performs quite well to detect and locate the position of the point when there occur no overlapping. The results of branch point detection are adequate for implementing to the robot. © 2015, Mechatronics and Machine Vision in Practice. All rights reserved.
