Robots and artificial intelligence technologies have become very important in the health applications as in many other fields. The proposed system in this work aims to provide detailed analysis of pre-op and post-op stage of FUE hair transplant procedures to enable surgeon to plan and assess success of the operations. In order to achieve this target, a robotic and vision-based system imaging and AI based analysis approach is developed. The proposed system performs analyses in three main stages: initialization, scanning, and analysis. At the initialization stage, 3D model of the patient’s head generated at first by locating a depth camera in various positions around the patient by the help of a collaborative robot. At the second stage, where high resolution image capturing is performed in a loop with the usage of the 3D model, raw images are processed by a deep learning based object detection algorithm where follicles in pre-op and extracted follicle positions (i.e. holes) and placed grafts in post-op is detected. At the last stage, thickness of each hair is computed at the detected hair follicle positions using another deep learning-based segmentation approach. These data are combined to obtain objective evaluation criteria to generate patient report. Experimental results show that the developed system can be used successfully in hair transplantation operations.

A fast motion estimation approach based on single sub-image bit-plane matching for low complexity image stabilization is presented in this paper. The recently proposed one-bit transform (IBT) based motion estimation method for digital image stabilization which employs multiple sub-images has lower computational complexity, however the motion estimation accuracy is relatively low. Single sub-image matching proposed in this paper enhances motion estimation performance without causing additional computational load. Furthermore, the multiplication operation required for IBT is avoided using a new kernel. The recently proposed constrained IBT (C-IBT) that restricts pixels with values adjacent to the transform threshold is employed to increase performance at the cost of a slightly higher computational load. Experimental results show that the proposed approach outperforms other sub-image based approaches

In this paper, a novel low bit-depth representation-based motion estimation approach with its hardware architecture is presented. The low bit-depth representation of pixels in the proposed method is constructed by choosing them from the gray-coded bit planes in an efficient way. Additionally, a new matching creation is also presented to improve the motion estimation accuracy. Thanks to the proposed binarization approach, the computation load is considerably reduced compared to filtering-based low bit-depth representation motion estimation methods. A novel hardware architecture for the proposed method is also presented in this paper. Experimental results revealed that the proposed motion estimation method and its hardware architecture provides a good balance between motion estimation accuracy and hardware resources especially for consumer electronics applications.