PHÁT TRIỂN LUẬT HỌC DÙNG CHO MẠNG NƠ RON TẾ BÀO BẬC CAO VÀ KHẢ NĂNG ỨNG DỤNG TRONG XỬ LÝ ẢNH

0 Người đánh giá. Xếp hạng trung bình 0

Tác giả: Đức Anh Dương, Hồng Vũ Nguyễn, Quang Hoan Nguyễn, Quang Trí Nguyễn, Tài Tuyên Nguyễn

Ngôn ngữ: vie

Ký hiệu phân loại:

Thông tin xuất bản: Tạp chí Khoa học và Công nghệ - Đại học Thái Nguyên, 2023

Mô tả vật lý: tr.172 - 180

Bộ sưu tập: Báo, Tạp chí

ID: 340240

Thêm vào giỏ Liên kết toàn văn

Mục đích của bài viết này là cải tiến một thuật toán học, được phát triển từ thuật toán học Perceptron hồi quy và thuật toán nhận dạng mẫu (dành cho Mạng nơ ron tế bào bậc cao). Phương pháp nghiên cứu của chúng tôi là phát triển lý thuyết học trong mạng nơ ron tế bào bậc cao và thử nghiệm các thuật toán. Kết quả nghiên cứu là hai thuật toán được cải tiến và bộ trọng số, ảnh xử lý được bằng hai thuật toán đó. Tập hợp các trọng số thu được từ thuật toán đã phát triển (tên là Thuật toán học Perceptron hồi quy bậc hai: SORPLA) có thể được sử dụng làm bộ lọc hoặc hạt nhân cho các vấn đề trong xử lý ảnh. Kết luận của bài báo như sau: Thứ nhất, sửa đổi thuật toán RPLA, bổ sung các mẫu bậc cao A và các mẫu bậc cao B
Thứ hai, cải thiện thuật toán xử lý hình ảnh PyCNN. Ngoài ra, bài báo cũng đề xuất khả năng ứng dụng của SORPLA trong phát hiện biên ảnh bằng cách sử dụng tập các trọng số thu được từ thuật toán đã phát triển cho Mạng nơ ron tế bào bậc cao.This paper aims at modifying a learning algorithm, developed from Recurrent Perceptron Learning Algorithm (RPLA) and a Pattern Recognition Algorithm for High-Order Cellular Neural Networks (HOCNN). Our research methods are developing theory of learning for high-order cellular neural networks and experiment with modified algorithms. The research results include two proposed algorithms and software which was built to test the two mentioned algorithms. The obtained set of the weights from our developed algorithm (named as Second-Order Recurrent Perceptron Learning Algorithm: SORPLA) can be used as filters or kernels for problems in imaging processing. In conclusion, firstly, the paper has modified the RPLA algorithm, which adds templates A and high-level templates B
secondly, it has improved the PyCNN image processing algorithm
finally, the paper also proposes an applicability of SORPLA in edge detection of image using the obtained set of the weights from the developed algorithm for the High-Order Cellular Neural Networks.

1. Đọc trực tuyến

1. Đọc trực tuyến

Tạo bộ sưu tập với mã QR