GIẢI PHÁP XỬ LÝ NHIỄU NGOẠI LAI TRONG KHÔI PHỤC ẢNH MỜ KHI CAMERA BỊ RUNG LẮC = OUTLIERS DISPOSING SOLUTION IN CAMERA-SHAKE IMAGE RESTORATION

0 Người đánh giá. Xếp hạng trung bình 0

Tác giả: Quang Thi Nguyễn, Thế Tiến Nguyễn, Xuân Phục Nguyễn, Công Mạnh Trần

Ngôn ngữ: vie

Ký hiệu phân loại:

Thông tin xuất bản: Tạp chí Khoa học và Công nghệ - Đại học Thái Nguyên, 2019

Mô tả vật lý:

Bộ sưu tập: NCBI

ID: 472784

Thêm vào giỏ

Hiện tượng ảnh bị mờ, nhòe khi chụp do camera bị rung lắc là một nguyên nhân phổ biến gây ra hiện tượng xuống cấp về chất lượng đối với ảnh số. Hơn nữa, việc bỏ qua nhiễu ngoại lai tồn tại trong các bức ảnh mờ sẽ tạo ra hiệu ứng rung (ringing) khi khôi phục ảnh. Để giải quyết những vấn đề này, bài báo đề xuất một phương pháp khôi phục ảnh mờ với việc xử lý các yếu tố nhiễu ngoại lai. Thuật toán đề xuất dùng các thống kê ảnh tự nhiên như là mô hình tiên nghiệm, kết hợp lý thuyết ước lượng Bayesian và phương pháp phân kỳ Kullback-Leibler để xây dựng nên hàm ước lượng nhằm tối ưu việc đánh giá nhân gây mờ (blur kernel). Thuật toán đồng thời cũng xem xét hiệu ứng rung gây ra bởi nhiễu ngoại lai, đề xuất dựa trên phương thức tối đa hóa kỳ vọng cho việc giải cuộn (deconvolution) nhằm giảm hiệu ứng rung. Kết quả thực nghiệm cho thấy sự hiệu quả của phương pháp được đề xuất và đưa ra một hướng tiếp cận mới trong khôi phục và xử lý ảnh mờ. Motion blur due to camera shaking during exposure is a common phenomena of image degradation. Moreover, neglecting the outliers that exist in the blurred image will result in the ringing effect of restored images. In order to solve these problems, a method for camera-shake blurred images restoration with disposing of outliers is proposed. The algorithm, which takes the natural image statistics as prior model, combines variational Bayesian estimation theory with Kullback-Leibler divergence to construct a cost function, can be easily optimized to estimate the blur kernel. Taking into consideration the ringing effect causing by outliers, an expectation-maximization based algorithm for deconvolution is proposed to reduce the ringing effect. The experimental results show that the method is practical and effective
this method also triggers the thinking about a new approach for blured image restoration.

Tạo bộ sưu tập với mã QR