System for object boundary detection using convolutional neural network (CNN) architecture, that performs canny edge detection, sobel operator, and watershed segmentation and paper describes how methods are limited in their ability to handle complex object shapes and occlusion
	KALIYAMURTHIE K P; SRI N G; REDDY D P P; GIRI B; RAJASEKH K; DHAN N; MUTHULAKSHMI K
	2023-10-16
专利权人	BHARATH HIGHER EDUCATION & RES INST (BHAR-Non-standard)
申请日期	2023-10-16
专利号	IN202341069688-A
成果简介	NOVELTY - The system that performs a canny edge detection, sobel operator, and watershed segmentation. A paper describes how the methods are limited in their ability to handle complex object shapes and occlusion. The traditional methods rely heavily on manual feature engineering and hyper parameter tuning which is time-consuming and tedious. The use of support vector machines (SVM) is mentioned for model development. USE - System for object boundary detection using convolutional neural network (CNN) architecture for real-world applications such as object recognition, segmentation tracking, and surveillance. ADVANTAGE - The system achieves high efficiency, time-saving processes, inexpensive techniques, low complexities and machine learning-based methods.
IPC 分类号	G06N-003/08 ; G06T-007/12 ; G06T-007/13 ; G06T-007/155 ; G06T-007/194
国家	印度
专业领域	信息技术
语种	英语
成果类型	专利
文献类型	科技成果
条目标识符	http://119.78.100.226:8889/handle/3KE4DYBR/19808
专题	中国科学院新疆生态与地理研究所
作者单位	BHARATH HIGHER EDUCATION & RES INST (BHAR-Non-standard)
推荐引用方式 GB/T 7714	KALIYAMURTHIE K P,SRI N G,REDDY D P P,et al. System for object boundary detection using convolutional neural network (CNN) architecture, that performs canny edge detection, sobel operator, and watershed segmentation and paper describes how methods are limited in their ability to handle complex object shapes and occlusion. IN202341069688-A[P]. 2023.

条目包含的文件
条目无相关文件。

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。