Matlab计算机视觉利器：VLFeat与MexOpenCV工具箱解析

版权申诉

5星 · 超过95%的资源 76 浏览量更新于2024-07-04 收藏 1.98MB PDF 举报

身份认证购VIP最低享 7 折!

领优惠券(最高得80元）

资源详情

资源推荐

The simple features used are reminiscent of Haar basis functions which

have been used by Papageorgiou et al. [10]. More specifically, we use three

kinds of features. The value of a two-rectangle feature is the difference

between the sum of the pixels within two rectangular regions. The regions

have the same size and shape and are horizontally or ver- tically adjacent

( see Figure 1 ). A three-rectangle feature computes the sum within two

outside rectangles subtracted from the sum in a center rectangle. Finally

a four-rectangle feature computes the difference between diagonal pairs of

rectangles.

上述简单特征是基于Haar基本函数设置的，Papageorgiou等⼈已使⽤过[10]。⽽我

们则是更具体地选择了特定的三类特征。其中，双矩形特征的值定义为两个矩形区域

⾥像素和的差。⽽区域则具有相同尺⼨和⼤⼩，并且⽔平或垂直相邻（如图1）。⽽三

矩形特征的值则是两个外侧矩形的像素和减去中间矩形的和所得的最终值。最后⼀个

四矩形特征的值是计算两组对⾓线矩形的区别⽽得的。

Given that the base resolution of the detector is 24×24, the exhaustive set

of rectangle features is quite large, over 180,000 . Note that unlike the Haar

basis, the set of rectan- gle features is overcomplete .

检测器的基本分辨率设定为24×24，既⽽得到数⽬巨⼤的矩形特征的完备集，超过了

180000。需要注意的是，矩形特征的集合不像Haar基底，它是过完备的。

Figure 1: Example rectangle

features shown relative to the enclosing detection window. The sum of the

pixels which lie within the white rectangles are subtracted from the sum of

pixels in the grey rectangles. Two-rectangle features are shown in (A) and

(B). Figure (C) shows a three-rectangle feature, and (D) a four-rectangle

feature.

矩形特征可以反映检测窗⼝之间的联系。⽩⾊矩形框中的像素和减去灰⾊矩形框内的

像素和得到特征值。(A)和(B)是矩形特征。(C)是三矩形特征。(D)是四矩形特征。

图 1

2.1. Integral Image

Rectangle features can be computed very rapidly using an intermediate

representation for the image which we call the integral image. The integral

image at location x, ycontains the sum of the pixels above and to the left

of x, y , inclusive:

（这⾥S(x,y)是⾏累积和 S(x,-1)=0， ii (-1,y)=0 ）积分图像可以通过已知原始图

像⽽⼀步求得。

Using the integral image any rectangular sum can be computed in four array

references (see Figure 2). Clearly the difference between two rectangular

sums can be computed in eight references. Since the two-rectangle features

defined above involve adjacent rectangular sums they can be computed in

six array references, eight in the case of the three-rectangle features, and

nine for four-rectangle features.

使⽤积分图像可以把任意⼀个矩形⽤四个数组计算(见图2)。显然两个矩形和之差可以

⽤⼋个数组。因为双矩形特征的定义是两个相邻矩形的和，所以仅⽤6个数组就可以计

算出结果。同理三矩形特征⽤8个，四矩形特征⽤9个。

2.2. Feature Discussion

Rectangle features are somewhat primitive when compared with alternatives

such as steerable filters [5, 7]. Steerable fil- ters, and their relatives, are

excellent for the detailed analy- sis of boundaries, image compression, and

texture analysis. In contrast rectangle features, while sensitive to the pres-

ence of edges, bars, and other simple image structure, are quite coarse.

Unlike steerable filters the only orientations available are vertical, horizontal,

and diagonal. The set of rectangle features do however provide a rich image

repre- sentation which supports effective learning. In conjunction with the

integral image , the efficiency of the rectangle fea- ture set provides ample

compensation for their limited flex- ibility.

2.2特征讨论

和⼀些相似⽅法，如导向滤波⽐较起来，矩形特征看似有些原始[5,7]。导向滤波等类

似⽅法，⾮常适合做对边界的详细分析，图像压缩，纹理分析。相⽐之下矩形特征，

对于边缘，条纹，以及其他简单的图像结构的敏感度，是相当粗糙的。不同于导向滤

波，它仅有的有效位置就是垂直，⽔平和对⾓线。矩形特征的设置做不过是提供了丰

富的图像表征，⽀持有效的学习。与积分图像⼀起，矩形特征的⾼效给它们有限的灵

活性提供了极⼤补偿。

3 . Learning Classification Functions

Given a feature set and a training set of positive and neg- ative images, any

number of machine learning approaches could be used to learn a

classification function. In our sys- tem a variant of AdaBoost is used both to

select a small set of features and train the classifier [6]. In its original form,

the AdaBoost learning algorithm is used to boost the clas- sification

performance of a simple (sometimes called weak) learning algorithm. There

are a number of formal guaran- tees provided by the AdaBoost learning

procedure. Freund and Schapire proved that the training error of the strong

classifier approaches zero exponentially in the number of rounds. More

importantly a number of results were later proved about generalization

performance [14]. The key insight is that generalization performance is

related to the margin of the examples, and that AdaBoost achieves large

margins rapidly.

剩余50页未读，继续阅读

_webkit

粉丝: 30
资源: 1万+

Matlab计算机视觉利器：VLFeat与MexOpenCV工具箱解析

matlab开发-计算机视觉功能提取工具箱

计算机视觉中的多视图几何.pdf(中文版+英文版+matlab程序)

MATLAB机器视觉工具箱

MATLAB中的图像处理基础与应用

matlab计算机视觉工具箱入门

matlab计算机视觉工具箱

MATLAB的图像处理工具箱怎么使用？

matlab 图像处理工具箱下载

matlab机器视觉工具箱

matlab 图像处理工具箱

matlab图像处理工具箱安装

matlab图像处理工具包

怎样加载图像处理工具箱

Matlab图像处理工具箱介绍

如何安装MATLAB的计算机视觉工具箱

matlab机器视觉图像处理

机器视觉图像处理matlab

如何调用matlab图像处理工具箱

matlab图像处理学习

matlab计算机视觉与深度学习实战 pdf csdn

最新资源