【正文】 應(yīng)注意，這些定義并不能保證在一幅圖像中成功地找到邊緣，它們只是給了我們一個(gè)尋找邊緣的形式體系。術(shù)語“邊緣線段”一般在邊緣與圖像的尺寸比起來很短時(shí)才使用。為了找到這些邊線，我們可以在圖像亮度梯度的二階導(dǎo)數(shù)中尋找過零點(diǎn)。在理想的連續(xù)變 化情況下，在二階導(dǎo)數(shù)中檢測(cè)過零點(diǎn)將得到梯度中的局部最大值。這 種方法假設(shè)邊緣是連續(xù)的界線，并且我們能夠跟蹤前面所看到的邊緣的模糊部分，而不會(huì)將圖像中的噪聲點(diǎn)標(biāo)記為邊緣。 一個(gè)常用的這種方法是帶有 滯后作用 的 閾值選擇 。與此相反，一個(gè)高的閾值將會(huì)遺失細(xì)的或者短的線段?；诹憬徊娴姆椒ㄕ业接蓤D像得到的二階導(dǎo)數(shù)的零交叉點(diǎn)來定位邊緣。而且，甚至可以認(rèn)為這個(gè)例子中存在多個(gè)邊緣。如果將邊緣認(rèn)為是一定數(shù)量點(diǎn)亮度發(fā)生變化的地方，那么邊緣檢測(cè)大體上就是計(jì)算這個(gè)亮度變化的導(dǎo)數(shù)。相反，它們通常受到一個(gè)或多個(gè)下面所列因素的影響： 場(chǎng)景深度 帶來的聚焦模糊； 半影模糊 ； 陰影 ； 邊緣附近的局部 鏡面反射 或者 漫反射 。相反單頭箭頭連接處理模塊。這一知識(shí)可能如圖像細(xì)節(jié)區(qū)域那樣簡(jiǎn)單，在這里，感興趣的信息被定位，這樣，限制性的搜索就被引導(dǎo)到尋找的信息處。 識(shí)別是基于目標(biāo)的描述給目標(biāo)賦以符號(hào)的過程。則某些應(yīng)用中，這些表示方法是互補(bǔ)的。無論哪種情況，把數(shù)據(jù)轉(zhuǎn)換成適合計(jì)算機(jī)處理的形式都是必要的。復(fù)雜的分割過程導(dǎo)致成功解決要求物體被分別識(shí)別出來的成像問題需要大量處理工作。 形態(tài)學(xué)處理設(shè)計(jì)提取圖像元素的工具，它在表現(xiàn)和描述形狀方面非常有用。在這里，圖像被成功地細(xì)分 為較小的區(qū)域。就使得在彩色模型、數(shù)字域的彩色處理方面涵蓋了大量基本概念。然而，不像增強(qiáng)，圖像增強(qiáng)是主觀的，而圖像復(fù)原是客觀的。基本上，增強(qiáng)技術(shù)后面的思 路是顯現(xiàn)那些被模糊了的細(xì)節(jié)，或簡(jiǎn)單地突出一幅圖像中感興趣的特征。 圖像獲取是第一步處理。 建立在電磁波譜輻射基礎(chǔ)上的圖像是最熟悉的，特別是 X 射線和可見光譜圖像。 數(shù)字圖像處理的應(yīng)用領(lǐng)域多種多樣，所以文本在內(nèi)容組織上盡量達(dá)到該技術(shù)應(yīng)用領(lǐng)域的廣度。舉一個(gè)簡(jiǎn)單的文本自動(dòng)分析方面的例子來具體說明這一概念。中級(jí)圖像處理是以輸入為圖像，但輸出是從這些圖像中提取的特征（如邊緣、輪廓及不同物體的標(biāo)識(shí)等）為特點(diǎn)的。然而，在這個(gè)連續(xù)的統(tǒng)一體中可以考慮三種典型的計(jì)算處理（即低級(jí)、中級(jí)和高級(jí)處理）來區(qū)分其中的各個(gè)學(xué)科。另一方面，有些領(lǐng)域（如計(jì)算機(jī)視覺）研究的最高目標(biāo)是用計(jì)算機(jī)去模擬人類 視覺，包括理解和推理并根據(jù)視覺輸入采取行動(dòng)等。 圖像處理涉及的范疇或其他相關(guān)領(lǐng)域（例如，圖像分析和計(jì)算機(jī)視覺）的界定在初創(chuàng)人之間并沒有一致的看法。 視覺是人類最高級(jí)的感知器官，所以，毫無疑問圖像在人類感知中扮演著最重要的角色。 一幅圖像可定義為一個(gè)二維函數(shù) f(x,y)，這里 x 和 y 是空間坐標(biāo)，而在任何一對(duì)空間坐標(biāo)（ x,y）上的幅值 f 稱為該點(diǎn)圖像的強(qiáng)度或灰度。 and processing of image data for storage, transmission, and representation for au tonomous machine perception. An image may be defined as a twodimensional function, f(x, y), where x and y are spatial (plane) coordinates, and the amplitude of f at any pair of coordinates (x, y) is called the intensity or gray level of the image at that point. When x, y, and the amplitude values of f are all finite, discrete quantities, we call the image a digital image. The field of digital image processing refers to processing digital images by means of a digital puter. Note that a digital image is posed of a finite number of elements, each of which has a particular location and value. These elements are referred to as picture elements, image elements, pels, and pixels. Pixel is the term most widely used to denote the elements of a digital image. Vision is the most advanced of our senses, so it is not surprising that images play the single most important role in human perception. However, unlike humans, who are limited to the visual band of the electromagic (EM) spec trum, imaging machines cover almost the entire EM spectrum, ranging from gamma to radio waves. They can operate on images generated by sources that humans are not accustomed to associating with images. These include ultra sound, electron microscopy, and putergenerated images. Thus, digital image processing enpasses a wide and varied field of applications. There is no general agreement among authors regarding where image processing stops and other related areas, such as image analysis and puter vi sion, start. Sometimes a distinction is made by defining image processing as a discipline in which both the input and output of a process are images. We believe this to be a limiting and somewhat artificial boundary. For example, under this definition, even the trivial task of puting the average intensity of an image (which yields a single number) would not be considered an image processing operation. On the other hand, there are fields such as puter vision whose ultimate goal is to use puters to emulate human vision, including learning and being able to make inferences and take actions based on visual inputs. This area itself is a branch of artificial intelligence (AI) whose objective is to emulate human intelligence. The field of AI is in its earliest stages of infancy in terms of development, with progress having been much slower than originally anticipated. The area of image analysis (also called image understanding) is in be tween image processing and puter vision. There are no clearcut boundaries in the continuum from image processing at one end to puter vision at the other. However, one useful paradigm is to consider three types of puterized processes in this continuum: low, mid, and highlevel processes. Lowlevel processes involve primitive opera tions such as image preprocessing to reduce noise, contrast enhancement, and image sharpening. A lowlevel process is characterized by the fact that both its inputs and outputs are images. Midlevel processing on images involves tasks such as segmentation (partitioning an image into regions or objects), description of those objects to reduce them to a form suitable for puter processing, and classification (recognition) of individual objects. A midlevel process is characterized by the fact that its inputs generally are images, but its outputs are attributes extracted from those images (., edges, contours, and the identity of individual objects). Finally, higherlevel processing involves “making sense” of an ensemble of recognized objects, as in image analysis, and, at the far end of the continuum, performing the cognitive functions normally associate