Action representation for robust human activity recognition is still a challenging problem. This thesis proposed a new feature for human activity recognition named SIFTMotion Estimation (SIFT-ME). SIFT-ME is derived from SIFT correspondences in a sequence of video frames and adds tracking information to describe human body motion. This feature is an extension of SIFT and is used to represent bo...

Why has SIFT been so successful? Why its extension, DSP-SIFT, can further improve SIFT? Is there a theory that can explain both? How can such theory benefit real applications? Can it suggest new algorithms with reduced computational complexity or new descriptors with better accuracy for matching? We construct a general theory of local descriptors for visual matching. Our theory relies on concep...

Action representation for robust human activity recognition is still a challenging problem. This thesis proposed a new feature for human activity recognition named SIFTMotion Estimation (SIFT-ME). SIFT-ME is derived from SIFT correspondences in a sequence of video frames and adds tracking information to describe human body motion. This feature is an extension of SIFT and is used to represent bo...

SIFT is an image local feature description algorithm based on scale-space. Due to its strong matching ability, SIFT has many applications in different fields, such as image retrieval, image stitching, and machine vision. After SIFT was proposed, researchers have never stopped tuning it. The improved algorithms that have drawn a lot of attention are PCA-SIFT, GSIFT, CSIFT, SURF and ASIFT. In thi...

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...

Object recognition has become one of the most active research topics in computer vision in recent years. The set of features extracted from the training image is critical for good object recognition performance. The Scale Invariant Feature Transform (SIFT) was proposed by David Lowe in 1999; the SIFT features are local and effective for object recognition. In this paper we conducted a survey of...

In the light of the deep analyses of subspace recognition and SIFT recognition, a novel image recognition based on subspace and SIFT is proposed to provide a recognition from global features to minutiae features. First, subspace is used to implement coarse image recognition, gaining one or more candidate samples with different identities. Then, a special SIFT recognition environment is designed...

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. ...

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 c...

Few distributed software-implemented fault tolerance (SIFT) environments have been experimentally evaluated using substantial applications to show that they protect both themselves and the applications from errors. This paper presents an experimental evaluation of a SIFT environment used to oversee spaceborne applications as part of the Remote Exploration and Experimentation (REE) program at th...