AE—Automation and Emerging Technologies: Co-occurrence Matrix Texture Features of Multi-spectral Images on Poultry Carcasses
✍ Scribed by B. Park; Y.R. Chen
- Publisher
- Elsevier Science
- Year
- 2001
- Tongue
- English
- Weight
- 825 KB
- Volume
- 78
- Category
- Article
- ISSN
- 0021-8634
No coin nor oath required. For personal study only.
✦ Synopsis
The variance, sum average, sum variance and sum entropy of co-occurrence matrix were the most signi"cant texture features (probability, P(0)0005) to identify unwholesome poultry carcasses at visible and near-infrared wavelengths. When a direction of co-occurrence matrix equals to 03, the contrast value was lower and the inverse di!erence moment and di!erence variance were higher (probability, P(0)01) than any other direction in the visible spectral images. The characteristics of variance and sum variance of spectral images varied with the wavelength of spectral images and unwholesomeness of poultry carcasses as well. The sum variance of wholesome was higher (probability, P(0)005) than unwholesome carcasses at the wavelength of both 542 and 570 nm. For the near-infrared spectral images at 847 nm, the sum average, entropy and sum entropy values of unwholesome carcasses were higher (probability, P(0)005) than wholesome ones. The linear discriminant model was able to identify unwholesome carcasses with classi"cation accuracy of 95)6%, while the quadratic model (97)0% accuracy) was better to identify wholesome carcasses.