Bag Of Visual Words 三大步
2014-08-05 22:24
337 查看
第一步:Feature detection
In computer
vision and image
processing the concept of feature detection refers
to methods that aim at computing abstractions of image information and making local decisions at every image point whether there is an image
feature of a given type at that point or not. The resulting features will be subsets of the image domain, often in the form of isolated points, continuous curves
or connected regions.
Common
feature detectors and their classification:
第二步:feature
description
After
feature detection, each image is abstracted by several local patches. Feature representation methods deal with how to represent the patches as numerical vectors. These vectors are called feature descriptors. A good descriptor should have the ability to handle
intensity, rotation, scale and affine variations to some extent. One of the most famous descriptors is Scale-invariant
feature transform (SIFT).SIFT converts each patch to 128-dimensional
vector. After this step, each image is a collection of vectors of the same dimension (128 for SIFT), where the order of different vectors is of no importance.
第三步:Codebook
generation
The final step for the BoW model is to convert vector represented patches to "codewords" (analogy to words in text documents), which also produces a "codebook" (analogy to a word dictionary). A codeword can
be considered as a representative of several similar patches. One simple method is performing k-means clustering over
all the vectors.[5] Codewords
are then defined as the centers of the learned clusters. The number of the clusters is the codebook size (analogy to the size of the word dictionary).
Thus, each patch in an image is mapped to a certain codeword through the clustering process and the image can be represented by the histogram of
the codewords.
In computer
vision and image
processing the concept of feature detection refers
to methods that aim at computing abstractions of image information and making local decisions at every image point whether there is an image
feature of a given type at that point or not. The resulting features will be subsets of the image domain, often in the form of isolated points, continuous curves
or connected regions.
Common
feature detectors and their classification:
Feature detector | Edge | Corner | Blob |
---|---|---|---|
Canny | X | ||
Sobel | X | ||
Harris & Stephens / Plessey | X | X | |
SUSAN | X | X | |
Shi & Tomasi | X | ||
Level curve curvature | X | ||
FAST | X | X | |
Laplacian of Gaussian | X | X | |
Difference of Gaussians | X | X | |
Determinant of Hessian | X | X | |
MSER | X | ||
PCBR | X | ||
Grey-level blobs | X |
description
After
feature detection, each image is abstracted by several local patches. Feature representation methods deal with how to represent the patches as numerical vectors. These vectors are called feature descriptors. A good descriptor should have the ability to handle
intensity, rotation, scale and affine variations to some extent. One of the most famous descriptors is Scale-invariant
feature transform (SIFT).SIFT converts each patch to 128-dimensional
vector. After this step, each image is a collection of vectors of the same dimension (128 for SIFT), where the order of different vectors is of no importance.
第三步:Codebook
generation
The final step for the BoW model is to convert vector represented patches to "codewords" (analogy to words in text documents), which also produces a "codebook" (analogy to a word dictionary). A codeword can
be considered as a representative of several similar patches. One simple method is performing k-means clustering over
all the vectors.[5] Codewords
are then defined as the centers of the learned clusters. The number of the clusters is the codebook size (analogy to the size of the word dictionary).
Thus, each patch in an image is mapped to a certain codeword through the clustering process and the image can be represented by the histogram of
the codewords.
相关文章推荐
- 视觉词袋 visual bag of words
- 基于BOW模型的图像分类Bag Of Visual Words model for image classification
- Bag of visual words(Bag of Words(BOW)模型)
- Bag of visual words(Bag of Words(BOW)模型)
- 基于Bow模型的图像检索 Image Retrieval with Bag of Visual Words
- 基于BoW模型的图像分类 Image Classification with Bag of Visual Words
- Bag of Words/Bag of Features
- SIFT算法的应用--目标识别之Bag-of-words模型
- 第九章三续:SIFT算法的应用--目标识别之Bag-of-words模型
- Kaggle情感分析(Bag of Words Meets Bags of Popcorn)
- bag of words
- 第九章三续:SIFT算法的应用--目标识别之Bag-of-words模型
- Bag of Words
- Bag of Words
- 目标识别之用Bag-of-words模型表示一幅图像
- 第九章三续:SIFT算法的应用--目标识别之Bag-of-words模型
- SIFT算法的应用--目标识别之Bag-of-words模型(转)
- bag of words
- 京东评论情感分类器(基于bag-of-words模型)
- SIFT算法的应用--目标识别之Bag-of-words模型