A Survey of Potatoes Image Segmentation Based on Machine Vision

A Survey of Potatoes Image Segmentation Based on Machine Vision

Navid Razmjooy (Independent Researcher, Belgium), Vania Vieira Estrela (Fluminense Federal University, Brazil) and Hermes Jose Loschi (State University of Campinas, Brazil)
DOI: 10.4018/978-1-5225-8027-0.ch001

Abstract

The quality control of the agricultural products, which in many cases is through intuitive observation of the visible features of the product, plays a key role in the survival of the agricultural industry. For a long time, the qualitative categorization of these products has been performed by trained people who search products for the specific characteristics. On the other hand, hard and repetitive working can cause people to make some mistakes in computing the quality control errors. Hence, by entering the machine vision systems into this subject, they turned into a reliable, low-cost and real-time technology. Despite the existence of machine vision systems in this process, there are still major challenges in categorizing agricultural products in terms of quality, size, shape, and examination of defects. Potato is one of the most important agricultural products that is produced and has a high application. Unfortunately, it suffers from various types of diseases and defects. Hence, its quality control has a particular importance.
Chapter Preview
Top

Bi-Level Image Segmentation

In order to obtain a simple and fast system, monochrome (grayscale) images are the best choice (Russ, 2016). Using grayscale images reduces the complexity and speeds up the system. There are different works of using this kind of system. The general algorithm of this approach is as follows:

  • 1.

    Image acquisition

  • 2.

    Convert image into the gray color space

  • 3.

    Image thresholding

  • 4.

    Performing the morphological operations

  • 5.

    Two level segmented image including potato tuber and background

In brief, after reading the image, it should be first converted to the gray color space. Figure 1 shows the gray mode for a simple image.

Figure 1.

(A) Input image (RGB color space) and (B) gray conversion of the (A)

978-1-5225-8027-0.ch001.f01

In Figure 2, the gray image should be threshold by a threshold technique to achieve a bilevel image including the potato and background. For instance, consider the previous image; by applying a threshold method (for example Otsu method is analyzed (Xu, Xu, Jin, & Song, 2011)) and the morphological operations, the output image including a highlighted potato tuber separated from its background is achieved.

Figure 2.

Grayscale image (A) and its threshold result after image threshold and morphological operations (B)

978-1-5225-8027-0.ch001.f02

Complete Chapter List

Search this Book:
Reset