Tài liệu Xử lý ảnh Đại học bách khoa HN

TRƯỜNG ĐẠI HỌC BÁCH KHOA HÀ NỘI XỬ LÝ ẢNH TRONG CƠ ĐIỆN TỬ Machine Vision Giảng viên: TS Mạc Thị Thoa Đơn vị: Bộ môn Cơ điện tử, Viện Cơ khí Hà Nội, 2020 Chapter Digital Image Fundamentals Image Sensing and Acquisition (cảm biến thu nhận hình ảnh) Image Sampling and Quantization (Lấy mẫu lượng tử hóa hình ảnh) Some Basic Relationships Between Pixels (Mối quan hệ điểm ảnh) Basic Mathematical Tools Used in Digital Image Processing (Các cơng cụ tốn học dùng xử lý ảnh số) Image Sensing and Acquisition Image Sensing and Acquisition (a) Single sensing element (b) Line sensor (c) Array sensor Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) Figure shows the three principal sensor arrangements used to transform incident energy into digital images (ba cách bố trí cảm biến sử dụng để biến đổi lượng tới thành hình ảnh kỹ thuật số) Image Sensing and Acquisition Image Acquisition Using a Single Sensing Element Combining a single sensing element with mechanical motion to generate a 2-D image Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) Image Sensing and Acquisition Image Acquisition Using Sensor Strips (Thu nhận hình ảnh sử dụng dải cảm biến) (a) Image acquisition using a linear sensor strip Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) (b) Image acquisition using a circular sensor strip Image Sensing and Acquisition Image Acquisition Using Sensor Arrays An example of digital image acquisition (a) Illumination (energy) source (b) A scene (c) Imaging system (d) Projection of the scene onto the image plane (e) Digitized image Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) Image Sensing and Acquisition Definition of Digital Image (Khái niệm ảnh số)  Ảnh số tập hợp hữu hạn điểm ảnh với mức xám phù hợp dùng để mô tả ảnh gần với ảnh thật  Tùy thuộc vào thông tin pixel, ảnh chia thành ảnh nhị phân, hình ảnh thang độ xám, ảnh RGB … Picture Element (Điểm ảnh)  Điểm ảnh (Pixel) phần tử ảnh số tọa độ (x,y) với độ xám màu định  Kích thước khoảng cách điểm ảnh chọn thích hợp cho mắt người cảm nhận liên tục không gian mức xám/ màu ảnh số gần ảnh thật  Mỗi phần tử ma trận gọi phần tử ảnh Image Sensing and Acquisition Sắc màu ảnh  Các màu sắc sở để dùng biểu diễn ảnh màu tạo thành hệ màu đề xuất dựa nghiên cứu thị giác người  Hệ màu RGB (Red, Green, Blue) mô hình phổ biến nhất, điểm ảnh biểu diễn giá trị thuộc khoảng [0 255] Image Sensing and Acquisition Sắc màu ảnh- Các mơ hình màu • Red, Green, Blue trục nhận giá trị [0 255] Mơ hình RGB biểu diễn 16 triệu màu Trong đó, R (255, 0, 0), G (0, 255, 0) B (0, 0, 255) • CMYK (Cyan, Magenta, Yellow, Black) với C = 255-R, M = 255-G, Y = 255-B • YCbCr Y = 16+219(0.299R+0.587G+0.114B)/255 Cb = 128+224(-0.169R-0.331G+0.5B)/255 Cr = 128+224(0.5R-0.419G-0.081B)/255 10 Basic Mathematical Tools Used in Digital Image Processing Basic Set Operations Set operations involving grayscale images (a) Original image (b) Image negative obtained using grayscale set complementation (c) The union of image (a) and a constant image Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 54 Basic Mathematical Tools Used in Digital Image Processing Logical Operations Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 55 Basic Mathematical Tools Used in Digital Image Processing Logical Operations Illustration of logical operations involving foreground (white) pixels Black represents binary 0’s and white binary 1’s The dashed lines are shown for reference only They are not part of the result Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 56 Basic Mathematical Tools Used in Digital Image Processing Single-Pixel Operations (a) An 8-bit image (b) Intensity transformation function used to obtain the digital equivalent of a “photographic” negative of an 8-bit image The arrows show transformation of an arbitrary input intensity value into its corresponding output value (c) Negative of (a), obtained using the transformation function in (b) Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 57 Basic Mathematical Tools Used in Digital Image Processing Neighborhood Operations Local averaging using neighborhood processing The procedure is illustrated in (a) and (b) for a rectangular neighborhood (c) An aortic angiogram (d) The result of using Eq (2) with m = m = 41 The images are of size 790 x 686 pixels (2) Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 58 Basic Mathematical Tools Used in Digital Image Processing Geometric Transformations Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 59 Basic Mathematical Tools Used in Digital Image Processing Geometric Transformations Phép biến dạng (Shearing) Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 60 Basic Mathematical Tools Used in Digital Image Processing Geometric Transformations (a) A 541 x 421 image of the letter T (b) Image rotated -210 using nearest-neighbor interpolation for intensity assignments (c) Image rotated -210 using bilinear interpolation (d) Image rotated -210 using bicubic interpolation (e)-(h) Zoomed sections (each square is one pixel, and the numbers shown are intensity values) Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 61 Basic Mathematical Tools Used in Digital Image Processing Geometric Transformations (a) A digital image (b) Rotated image (note the counterclockwise direction for a positive angle of rotation) (c) Rotated image cropped to fit the same area as the original image (d) Image enlarged to accommodate the entire rotated image Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 62 Basic Mathematical Tools Used in Digital Image Processing Image Registration Image registration (a) Reference image (b) Input (geometrically distorted image) Corresponding tie points are shown as small white squares near the corners (c) Registered (output) image (note the errors in the border) (d) Difference between (a) and (c), showing more registration errors Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 63 Basic Mathematical Tools Used in Digital Image Processing Vector and Matrix Operations Forming a vector from corresponding pixel values in three RGB component images Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 64 Basic Mathematical Tools Used in Digital Image Processing Image Transforms  2-D linear transforms  Inverse transform Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 65 Basic Mathematical Tools Used in Digital Image Processing Image Transforms General approach for working in the linear transform domain Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 66 Basic Mathematical Tools Used in Digital Image Processing Image Transforms (a) Image corrupted by sinusoidal interference (b) Magnitude of the Fourier transform showing the bursts of energy caused by the interference (the bursts were enlarged for display purposes) (c) Mask used to eliminate the energy bursts (d) Result of computing the inverse of the modified Fourier transform Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 67 CÂU HỎI ÔN TẬP Nêu khái niệm định nghĩa điểm ảnh Thế độ phân giải ảnh, cho ví dụ? Trình bày định nghĩa mức xám, cho ví dụ Nêu quan hệ điểm ảnh Trình bày khoảng cách đo phân loại khoảng cách điểm ảnh Nêu ý nghĩa phép biến đổi ảnh, liệt kê số phép biến đổi cho ví dụ ... ? ?Digital image processing,” Pearson (2018) 30 Image Sampling and Quantization Representing Digital Images (a) Image plotted as a surface (b) Image displayed as a visual intensity array (c) Image. .. ? ?Digital image processing,” Pearson (2018) 32 Image Sampling and Quantization Representing Digital Images Rafael C Gonzalez, Richard E Woods, ? ?Digital image processing,” Pearson (2018) 33 Image. .. Woods, ? ?Digital image processing,” Pearson (2018) (b) Image acquisition using a circular sensor strip Image Sensing and Acquisition ? ?Image Acquisition Using Sensor Arrays An example of digital image