Search

Digital image processing has numerous applications in many sectors of the world. It expands from initial information registration into methods and thoughts combining pattern recognition, computer vision, and machine learning. The wide utilization has pulled in many researchers to integrate with a range of related specializations. This work gives a study of the latest development and theoretical ideas clarifying an improvement of computer vision particularly with pattern recognition and image processing, utilizing various regions of their field implementation. Digital image processing causes researchers to analyze images to get important data and comprehend information. It utilized a technique of multi-range implementation and huge information analysis. This work aims to focus on the latest studies related to image processing, pattern recognition, and computer vision. In this paper, Computer vision standard has been categorized into groups. For example, pattern recognition, image processing, and AI. Additionally, we give a short clarification of the forward-thinking data about the methods and their realization. This survey is restricted to computer vision, and more research can include detecting the conduct and properties of the object including people actions.

The Butterfly Optimization Algorithm is one of the most recent nature-inspired algorithms that mimic the butterflies' behavior in mating and finding food, for solving the global optimization problems. The algorithm utilizes the sense of butterflies of smelling for determining the location of nectar and find mates, which is based on the foraging strategy of those insects. This paper represents a method of using the BOA algorithm for solving the problem of path planning in three-dimensional space. The proposed method finds a path from a particular starting point to any chosen goal, where the generated final path is completely safe and collision-free. The algorithm is based on 3 phases: the initial phase, the iteration phase, and the final phase. The movement of butterflies is based on two search moves, one of them is Local random search; where the butterfly moves randomly within the swarm, and the other is Global search; where the butterfly moves towards the best-fitted butterfly in the current population. The proposed method in this paper is able to find a collision-free path from the start point to the goal in all of the presented test environments in proximately well performance and the results were computed in terms of execution time and path length.