Measures of Image and Video Segmentation

Measures of Image and Video Segmentation

Pushpajit A. Khaire (SRCOEM, India) and Roshan R. Kotkondawar (GCOE, India)
Copyright: © 2017 |Pages: 26
DOI: 10.4018/978-1-5225-1022-2.ch002
OnDemand PDF Download:
No Current Special Offers


Study on Video and Image segmentation is currently limited by the lack of evaluation metrics and benchmark datasets that covers the large variety of sub-problems appearing in image and video segmentation. Proposed chapter provides an analysis of Evaluation Metrics, Datasets for Image and Video Segmentation methods. Importance is on wide-ranging, Datasets robust Metrics which used for evaluation purposes without inducing any bias towards the evaluation results. Introductory Section discusses traditional image and video segmentation methods available, the importance and need of measures, metrics and dataset required to evaluate segmentation algorithms are discussed in next section. Main focus of the chapter explains the measures, metrics and dataset available for evaluation of segmentation techniques of both image and video. The goal is to provide details about a set of impartial datasets and evaluation metrics and to leave the final evaluation of the evaluation process to the understanding of the reader.
Chapter Preview


This introductory section will express the notions of digital image and digital video, with the importance of both in today’s age, it will also describe the importance of datasets and objective measures for evaluation of image segmentation and video segmentation techniques. According to (Jain, 1989) the term Digital Image Processing generally refers to processing of a two dimensional picture by a digital computer and in a broader sense, it implies digital processing of any two-dimensional data. A digital image is an array of real or complex numbers represented by a finite number of bits. (Pratt, 2007) describes segmentation of an image as it entails the division or separation of the image into regions of similar attribute and the most basic attribute for segmentation is image luminance amplitude for a monochrome image and color components for a color image. Important features called edges and other attribute like texture are also useful for segmentation.

Digital images and videos are, respectively, defined as pictures and movies that have been converted into a computer-readable binary format consisting of logical 0s and 1s. Theoretically an image is understood by a still picture that does not change with time, and a video is created by number of frames or images that changes with time, mostly containing moving and/or changing objects (Bovik, 2000). Digital images or video are usually obtained by converting continuous signals into digital format, although “direct digital” systems are becoming more prevalent. Likewise, digital visual signals are viewed by using diverse display media, including digital printers, computer monitors, and digital projection devices. Due to rapid increasing of multimedia in the form of text and moreover in the form of images and video this information is transmitted, stored, processed, and displayed in a digital visual format, and thus the design of engineering methods for efficiently transmitting, maintaining, and even improving the visual integrity of this information is of utmost interest (Bovik, 2000).

Complete Chapter List

Search this Book: