Realization Law of Pragnanz and Closure of gestalt theory using Active Learning Method
Publish place: International Conference on Engineering and Computer Science
Publish Year: 1395
نوع سند: مقاله کنفرانسی
زبان: English
View: 508
This Paper With 6 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ICCSE01_138
تاریخ نمایه سازی: 14 شهریور 1396
Abstract:
This paper presents a new algorithm for predicting missing parts of images. We investigate two laws of one of the well-known theories about visual system called Gestalt theories. These theories tried to define how a biological neural network can perform. Active Learning Method (ALM) is used as an artificial intelligent approach to realize law of Pragnanz and Closure principle of Gestalt theory. ALM is a pattern-based algorithm for soft computing which uses the Ink Drop Spread (IDS) algorithm. The present framework learns the patterns in an unsupervised manner or alongside any supervised task according to symmetry and pattern of rest of shape without considering unnecessary details. This method inspired by Morphology and used ALM as an iterative process. At each iteration the proposed algorithm finds Center of Gravity (COG) and the accuracy requirement can be achieved based on distances between centers to predict removed segment of image.
Keywords:
Authors
Negin Safaei
Artificial Creatures Lab, Sharif University of Technology Tehran, Iran
Saeid Bagheri Shouraki
Department of Electrical Engineering, Sharif University of Technology Tehran, Iran