Applications of Image Compression on Agricultural Image Data Analysis

Applications of Image Compression on Agricultural Image Data Analysis

K. Seetharaman (Annamalai University, India)
DOI: 10.4018/978-1-5225-8027-0.ch009

Abstract

With the advent of the cutting-edge technologies in information repository and communication, data storage is rapidly increased, and it is required to reduce the size of the data. Especially in the case of agricultural image data like types of plants, crops, seeds; kinds of diseases and their remedial pesticides; and the agricultural satellite; images require a huge volume of memory space to store. To avoid this problem, it is required to reduce the size of the data and redundancy of the data. To overcome this problem, this chapter proposes a compression method, based on an adaptive Gaussian Markov random field model for agricultural image data compression, where the images are assumed to be a Gaussian Markov random field. The parameters of the model are estimated, based on the Bayesian approach. The authors use arithmetic coding to store seed values and parameters of the model as it augments the compression ratio. They also have studied the use of the M-H algorithm, which updates the parameters and through which the image contents such as untexturedness are captured.
Chapter Preview
Top

Background

The preceding decades witnessed the influx of a considerable amount of technologies have been developed for agribusiness (Fountas et al., 2015) and ranging from embedded systems to networking technologies (Munack & Speckmann, 2001), more and more advanced electronics and communication methodologies continue to be added (Pereira et al., 2010; Steinberger et al., 2009). Though the technology in communication has been developed up to some extent, it does not satisfy both data transmission and storage. Therefore, the researchers in computer vision developed the data reduction techniques based on visual data characteristics. The data reduction, that is, data compression method satisfies both rapid transmission of data and minimizing the storage space, whereas the network communication technology helps to speed up the data transmission only. In the agricultural domain, this problem was first envisioned by (Stone, 1994), who introduced the use of agrarian networks using buses of higher bandwidth or multiple of buses. However, these solutions have not addressed the problems either accordingly nor are suitable to the ISO 11783 compression standard. In this respect, an alternative option is to shrink the amount of data to be transferred, as happens with in-vehicle networks (Miucic et al., 2009; Ramteke & Mahmud, 2005), e.g., via the employment of data compression methods. The data compression technique is more effective and efficient for data storage and transmission, which is effectively adopted in the agricultural domain

Key Terms in this Chapter

Image Descriptor: Set of features used to describe a scene or object.

Metropolis-Hastings (M-H) Algorithm: Markov Chain Monte Carlo (MCMC) scheme for attaining a sequence of random samples following a given probability distribution whose direct sampling is problematic.

Image compression: It is the process of reducing the size of an image of video by means of redundant information.

Markov Random Field: Undirected graphical model containing a set of random variables with the Markov property that can be represented by an undirected graph.

Texture: It is the nature of a surface defined by the small, local deviations from the perfectly flat ideal. It provides information about the spatial organization of color or brightness patterns in an image or particular region of an image.

Handcrafted Image Descriptor: An image descriptor where the set of features is handpicked by the designer of the algorithm.

Compression Ratio: It measures the relation between the number of bits for an image after decompression and its original size.

Complete Chapter List

Search this Book:
Reset