图像处理_Berkeley Segmentation Dataset and Benchmark500 (BSDS500)(Berkeley分割数据集和基准500 (BSDS500) ).pdfVIP

Berkeley Segmentation Dataset and Benchmark500 (BSDS500)(Berkeley 分割数据集和基准500 (BSDS500) ) 数据摘要： A large dataset of natural images that have been segmented by human observers. This dataset serves as ground truth for learning grouping cues as well as a benchmark for comparing different segmentation and boundary finding algorithms. 中文关键词： 数据库,边缘检测,图像分割,视频分割, 英文关键词： Database,contour detection,image segmentation,vedio segmation, 数据格式： TEXT 数据用途： Resources for contour detection and image segmentation.Serves as ground truth for learning grouping cues as well as a benchmark for comparing different segmentation and boundary finding algorithms. 数据详细介绍： Berkeley Segmentation Dataset and Benchmark Abstract : A large dataset of natural images that have been segmented by human observers. This dataset serves as ground truth for learning grouping cues as well as a benchmark for comparing different segmentation and boundary finding algorithms. The dataset consists of 500 natural images, ground-truth human annotations and benchmarking code. The data is explicitly separated into disjoint train, validation and test subsets. In order to preserve the integrity of the evaluation and obtain a direct and fair comparison of your results with existing methods, the guidelines below must be followed:  Train only on trainval: All the learning, parameter tuning, model selection, etc. should be done exclusively on the train and validation subsets of the data.  Run once on test: After training, your algorithm should be run only once with fixed parameters on the test subset of the data. The images and ground-truth segmentations of the test set cannot be used for tuning your algorithm.  Report all the evaluation results: Evaluate your results on the test subset with