Image Classification with Max-sift Descriptors
نویسندگان
چکیده
In the conventional Bag-of-Features (BoF) model for image classification, handcrafted descriptors such as SIFT are used for local patch description. Since SIFT is not flipping invariant, left-right flipping operation on images might harm the classification accuracy. To deal with, some algorithms augmented the training and testing datasets with flipped image copies. These models produce better classification results, but with the price of increasing time/memory consumptions. In this paper, we present a simple solution that uses Max-SIFT descriptors for image classification. Max-SIFT is a flipping invariant descriptor which is obtained from the maximum of a SIFT descriptor and its flipped copy. With Max-SIFT, more robust classification models could be trained without dataset augmentation. Experimental results reveal the consistent accuracy gain of Max-SIFT over SIFT. The much cheaper computational cost also makes it capable of being applied onto large-scale classification tasks.
منابع مشابه
New colour SIFT descriptors for image classification with applications to biometrics
This paper first presents a new oRGB-SIFT descriptor, and then integrates it with other color SIFT features to produce the novel Color SIFT Fusion (CSF) and the Color Grayscale SIFT Fusion (CGSF) descriptors for image classification with special applications to biometrics. Classification is implemented using a novel EFM-KNN classifier, which combines the Enhanced Fisher Model (EFM) and the K Ne...
متن کاملA New Color SIFT Descriptor and Methods for Image Category Classification
We first propose in this paper a new oRGB-SIFT descriptor, and then integrate it with other color SIFT features to produce the Color SIFT Fusion (CSF) and the Color Grayscale SIFT Fusion (CGSF) methods for image category classification. The effectiveness of our proposed representation and methods are evaluated on three representative, large scale, and grand challenging datasets. The experimenta...
متن کاملPerformance evaluation of block-based copy- move image forgery detection algorithms
Copy-move forgery is a particular type of distortion where a part or portions of one image is/are copied to other parts of the same image. This type of manipulation is done to hide a particular part of the image or to copy one or more objects into the same image. There are several methods for detecting copy-move forgery, including block-based and key point-based methods. In this paper, a method...
متن کاملRobust Image Matching with Selected SIFT Descriptors
A robust image matching algorithm using a set of selected SIFT descriptors is investigated in this work. We first utilize the colorbased segmentation method and the watershed algorithm to separate foreground and background regions in images and then search the corresponding SIFT descriptors along foreground contours. These selected SIFT descriptors can offer more robust and stable image matchin...
متن کاملColor Independent Components Based SIFT Descriptors for Object/Scene Classification
In this paper, we present a novel color independent components based SIFT descriptor (termed CIC-SIFT) for object/scene classification. We first learn an efficient color transformation matrix based on independent component analysis (ICA), which is adaptive to each category in a database. The ICA-based color transformation can enhance contrast between the objects and the background in an image. ...
متن کامل