Tài liệu xử lý ảnh Đại học Bách Khoa Hà Nội

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 Color Image Processing Color Fundamentals Color Models Pseudocolor Image Processing Basics of Full-Color Image Processing Color Transformations Color Image Smoothing and Sharpening Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) Color Fundamentals Color spectrum Color spectrum seen by passing white light through a prism(lăng kính) Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) Color Fundamentals Wavelengths Wavelengths comprising the visible range of the electromagnetic spectrum (quang phổ) Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) Color Fundamentals The absorption of light by the red, green, and blue cones (tế bào hình nón) in the eye Absorption of light by the red, green, and blue cones in the human eye as a function of wavelength Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) Color Fundamentals Primary and secondary colors of light and pigments (mảng màu) Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) Color Fundamentals Hue (tông màu), Saturation (độ bão hòa màu), and Brightness (độ sáng)  The characteristics generally used to distinguish one color from another are brightness, hue, and saturation  Brightness embodies the achromatic notion of intensity  Hue màu sắc mà nhìn thấy phụ thuộc vào bước sóng ánh sáng phản xạ sản xuất Màu sắc đo theo góc xếp hình trịn giúp dễ cảm nhận thay đổi so với hệ tọa độ RGB  Saturation Nó đơn giản cách màu sắc hiển thị điều kiện ánh sáng khác Saturation giúp miêu tả màu sắc đậm hay nhạt theo cường độ ánh sáng mạnh – nhẹ khác  Hue and saturation taken together are called chromaticity  a color may be characterized by its brightness and chromaticity Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 10 Pseudocolor Image Processing Intensity to Color Transformations  EXAMPLE: Using pseudocolor to highlight explosives in X-ray images These sinusoidal functions contain regions of relatively constant value around the peaks as well as regions that change rapidly near the valleys Changing the phase and frequency of each sinusoid can emphasize (in color) ranges in the grayscale For instance, if all three transformations have the same phase and frequency, the output will be a grayscale image A small change in the phase between the three transformations produces little change in pixels whose intensities correspond to peaks in the sinusoids, especially if the sinusoids have broad profiles (low frequencies) Pixels with intensity values in the steep section of the sinusoids are assigned a much stronger color content as a result of significant differences between the amplitudes of the three sinusoids caused by the phase displacement between them Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) Fig.7.23 Transformation functions used to obtain the pseudocolor images in Fig 7.22 37 Pseudocolor Image Processing Intensity to Color Transformations A pseudocolor coding approach using multiple grayscale images The inputs are grayscale images The outputs are the three components of an RGB composite image Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 38 Pseudocolor Image Processing Intensity to Color Transformations  EXAMPLE: Color coding of multispectral images (a)–(d) Red (R), green (G), blue (B), and nearinfrared (IR) components of a LANDSAT multispectral image of the Washington, D.C area (e) RGB color composite image obtained using the IR, G, and B component images (f) RGB color composite image obtained using the R, IR, and B component images four satellite images of the Washington, D.C., area, including part of the Potomac River Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 39 Pseudocolor Image Processing Intensity to Color Transformations  EXAMPLE: Color coding of multispectral images (a) Pseudocolor rendition of Jupiter Moon Io (b) A close-up Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 40 Basics of Full-Color Image Processing  Let c represent an arbitrary vector in RGB color space:  In order for per-component-image and vector-based processing to be equivalent, two conditions have to be satisfied: (1) the process has to be applicable to both vectors and scalars; (2) the operation on each component of a vector (i.e., each voxel) must be independent of the other components Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 41 Basics of Full-Color Image Processing Spatial neighborhoods for grayscale and RGB color images Observe in (b) that a single pair of spatial coordinates, (x, y), addresses the same spatial location in all three images Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 42 Color Transformations Formulation  Color transformations for multispectral images where n is the total number of component images, ri are the intensity values of the input component images, si are the spatially corresponding intensities in the output component images, and Ti are a set of transformation or color mapping functions that operate on ri to produce si For example, in the case of RGB color images, are the intensities values at a point in the input components images, and are the corresponding transformed pixels in the output image In principle, we can implement a different transformation for each input component image Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) A full-color image and its various color-space components 43 Color Transformations Formulation Adjusting the intensity of an image using color transformations (a) Original image (b) Result of decreasing its intensity by 30% (i.e., letting k = 0.7) (c) The required RGB mapping function (d)–(e) The required CMYK mapping functions (f) The required CMY mapping function (g)–(h) The required HSI mapping functions Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 44 Color Transformations Color Complements Color complements on the color circle Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) EXAMPLE: Computing color image complements Color complement transformations (a) Original image (b) Complement transformation functions (c) Complement of (a) based on the RGB mapping functions (d) An approximation of the RGB complement using HSI transformations 45 Color Transformations Color Slicing  Using a cube of width W  Using a sphere of radius R0 Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 46 Color Transformations Color Slicing EXAMPLE: Color slicing  Using a cube of width W  Using a sphere of radius R0 Color-slicing transformations that detect (a) reds within an RGB cube of width centered at (0.6863, 0.1608, 0.1922), and (b) reds within an RGB sphere of radius 0.1765 centered at the same point Pixels outside the cube and sphere were replaced by color (0.5, 0.5, 0.5) Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 47 Color Transformations Histogram Processing of Color Images  EXAMPLE: Histogram equalization in the HSI color space Histogram equalization (followed by saturation adjustment) in the HSI color space Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 48 Color Image Smoothing and Sharpening Color Image Smoothing  The average of the RGB component vectors in this neighborhood is Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 49 Color Image Smoothing and Sharpening Color Image Smoothing  EXAMPLE: Color image smoothing by neighborhood averaging HSI components of the RGB color image (a) Hue (b) Saturation (c) Intensity (a) RGB image (b) Red component image (c) Green component (d) Blue component Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) Image smoothing with a averaging kernel (a) Result of processing each RGB component image (b) Result of processing the intensity component of the HSI image and converting to RGB (c) Difference between the two results 50 Color Image Smoothing and Sharpening Color Image Sharpening  EXAMPLE: Image sharpening using the Laplacian Image sharpening using the Laplacian (a) Result of processing each RGB channel (b) Result of processing the HSI intensity component and converting to RGB (c) Difference between the two results Rafael C Gonzalez, Richard E Woods, “Digital image processing,” Pearson (2018) 51 .. .Chapter Color Image Processing Color Fundamentals Color Models Pseudocolor Image Processing Basics of Full -Color Image Processing Color Transformations Color Image Smoothing and... “Digital image processing, ” Pearson (2018) 13 Color Models ? ?Color model  The purpose of a color model (also called a color space or color system) is to facilitate the specification of colors in... “Digital image processing, ” Pearson (2018) 24 Color Models The HSI Color Model  Converting Colors from RGB to HSI Rafael C Gonzalez, Richard E Woods, “Digital image processing, ” Pearson (2018) 25 Color