Application of an Improved Hough Transform and Image Correction Algorithm in ACC

Abstract

Numerous studies have shown that ACC (Augmentative and Alternative Communication), as a tool in language and communication training for children with autism, has effectively improved and played a positive role. ACC’s Picture Exchange System (PECS) provides an important support for the correction and feature recognition of language and training teaching cards. When designing the picture exchange function of ACC, this paper proposes a modified Hough transform and image correction algorithm suitable for teaching cards to solve the problems of large data calculation, time-consuming calculation, large space occupation and false peaks caused by traditional Hough transform algorithm in detecting straight lines, which also optimizes the interactive experience of the teaching scene. Finally, we design two experiments to compare and analyse the classic Hough transform, random Hough transform and improved Hough transform. Experimental results show that the improved Hough transform algorithm has superior performance in terms of execution efficiency and accuracy of line detection.