Semi-Optimal Edge Detector based on Simple Standard Deviation with Adjusted Thresholding
This paper proposes a novel method which combines both median filter and simple standard deviation to accomplish an excellent edge detector for image processing. First of all, a denoising process must be applied on the grey scale image using median filter to identify pixels which are likely to be contaminated by noise. The benefit of this step is to smooth the image and get rid of the noisy pixels. After that, the simple statistical standard deviation could be computed for each 2X2 window size. If the value of the standard deviation inside the 2X2 window size is greater than a predefined threshold, then the upper left pixel in the 2?2 window represents an edge. The visual differences between the proposed edge detector and the standard known edge detectors have been shown to support the contribution in this paper.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingSimilar Papers 제목 키워드 기반
Cloud Object Detector Adaptation by Integrating Different Source Knowledge
We propose to explore an interesting and promising problem, Cloud Object Detector Adaptation (CODA), where the target domain leverages detections provided by a large cloud model to build a target detector. Despite with p…
Domain AdaptationKnowledge DistillationObject DetectionPolite Teacher: Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholding
We present Polite Teacher, a simple yet effective method for the task of semi-supervised instance segmentation. The proposed architecture relies on the Teacher-Student mutual learning framework. To filter out noisy pseud…
Instance SegmentationPseudo LabelSegmentationSemantic Segmentation+1Efficient Teacher: Semi-Supervised Object Detection for YOLOv5
Semi-Supervised Object Detection (SSOD) has been successful in improving the performance of both R-CNN series and anchor-free detectors. However, one-stage anchor-based detectors lack the structure to generate high-quali…
Objectobject-detectionObject DetectionPseudo Label+1Unsupervised Learning of Edges
Data-driven approaches for edge detection have proven effective and achieve top results on modern benchmarks. However, all current data-driven edge detectors require manual supervision for training in the form of hand-la…
Edge DetectionFormMotion Estimationobject-detection+1Distilling Image Classifiers in Object Detectors
Knowledge distillation constitutes a simple yet effective way to improve the performance of a compact student network by exploiting the knowledge of a more powerful teacher. Nevertheless, the knowledge distillation liter…
Knowledge DistillationObjectobject-detectionObject Detection+1