经过Canny算子边界提取后的图像，对于边界点求方向角，公式如下： 其中g(i,j)为经过高斯滤波后图像的灰度。以5度为单位，将360度的角度空间量化为72级，计算每个边界点处法向量的方向角分别落在这72级空间中的频率，这样便得到了边界方向直方图H。 边界方向不受图像中对象的位置的影响，为了达到不受图像缩放的影响，对得到的边界方向直方图进行归一化处理：H=H/S。其中H[I]为边界方向直方图，S为图像的面积。 边界方向直方图很显然受到图像旋转的影响，为了减少图像旋转对于直方图的影响，我们对直方图进行平滑：...

SIFT: Scale Invariant Feature Transform by Utkarsh in Computer Vision,Featured Matching features across different images in a common problem in computer vision. When all images are similar in nature (same scale, orientation, etc) simple corner detectors can work. But when you have images of different scales and rotations, you need to use the Scale Invariant Feature Transform. Why care about SIFT SIFT isn’t just scale invariant. You can change the following, and still...

转自http://mindhacks.cn/。 概率论只不过是把常识用数学公式表达了出来。 ——拉普拉斯 记得读本科的时候，最喜欢到城里的计算机书店里面去闲逛，一逛就是好几个小时；有一次，在书店看到一本书，名叫贝叶斯方法。当时数学系的课程还没有 学到概率统计。我心想，一个方法能够专门写出一本书来，肯定很牛逼。后来，我发现当初的那个朴素归纳推理成立了——这果然是个牛逼的方法。 ——题记 目录 0. 前言 1. 历史 1.1 一个例子：自然语言的二义性 1.2 贝叶斯公式 2. 拼写纠正 3. 模型比较与贝叶斯奥卡姆剃刀 3.1 再访拼...

http://www.keyanshequ.com/thread-78-1-1.html

下面是内容和要求： A faculty member in the School of Computer Engineering in Nanyang Technological University, Singapore, is recruiting one (1) Ph.D. student to work in the area of computer vision and/or machine learning. Self-motivating student is expected. The student will work on computer vision tasks using data-centered approach (e.g. object detection, or visual place categorization). Solid mathematical knowledge and familiarity with basic computer vision and machine l...

==Call for Papers: NIPS 2009 Workshop on Transfer Learning for Structured Data (TLSD-09)== in conjunction with NIPS 2009, Dec 7-12, 2009, Vancouver, B.C., Canada http://www.cse.ust.hk/~sinnopan/nips09tlsd/ Description and background ------------------------ Recently, transfer learning (TL) has gained much popularity as an approach to reduce the training-data calibration effort as well as improve generalization performance of learning tasks. Unlike traditional learning, tra...

由于是导师给的  所以比较珍贵 英文论文投稿前的经典28个细节检查 http://www.keyanshequ.com/thread-55-1-1.html

周志华的一篇关于怎样做研究的报告，前半部分主要讲选题，后半部分将怎样写论文，非常经典。 是在给我们作报告的时候我拷贝的PPT 资源丢失