In this paper, a novel Galois Field-based approach is proposed for rotation and scale invariant texture classification. The commutative and associative properties of Galois Field addition operator are useful for accomplishing the rotation and scale invariance of texture representation. Firstly, the Galois field operator is constructed, which is applied to the input textural image. The normalized cumulative histogram is constructed for Galois Field operated image. The bin values of the histogram are considered as rotation and scale invariant texture features. The classification is performed using the K-Nearest Neighbour classifier. The experimental results of the proposed method are compared with that of Rotation Invariant Local Binary Pattern (RILBP) and Log-Polar transform methods. These results obtained using the proposed method are encouraging and show the possibility of classifying texture successfully irrespective of its rotation and scale.

No abstract

No abstract

Sugar is a versatile and irreplaceable functional ingredient in the food. In addition to providing sweetness, sugar is also used to balance acidity and the production of medication. Sugarcane is obtained from farmers with the aid of vehicles as part of the sugar-producing process. The sugar industry maintains details of the sugarcane collection, payment, and orders of sugar cane products provided by the sugar industry are maintained by manually. The problem is that there is still not a single application that can manage all the processes related to the sugar industry such as sugarcane collection, sales, payments, and product stock. This system is a part of a revival process of the existing system. The system is to provide the sugar industry with an outline of the solution and breakdown of the proposed strategy for new system implementation.

This article presents a novel approach for illumination and rotation invariant texture representation for face recognition. A gradient transformation is used as illumination invariance property and a Galois Field for the rotation invariance property. The normalized cumulative histogram bin values of the Gradient Galois Field transformed image represent the illumination and rotation invariant texture features. These features are further used as face descriptors. Experimentations are performed on FERET and extended Cohn Kanade databases. The results show that the proposed method is better as compared to Rotation Invariant Local Binary Pattern, Log-polar transform and Sorted Local Gradient Pattern and is illumination and rotation invariant.