Shape is one of the main low level features in content based image retrieval systems (CBIR). This paper proposes a novel CBIR technique based on shape feature. In this technique feature extraction is based on a rectangle that covers a shape. The proposed signature is a Fourier based technique and it is invariant against translation, scaling and rotation. The retrieval performance between some c...

We propose a two-step Event-Level Feature (ELF) learning framework for automatic detection of semantic events. In the first step an elementary-level feature is generated to represent images and videos. Then in the second step an ELF is constructed on top of the elementary features to model each event as a feature vector. Semantic event detectors can be built based on the ELF. Various ELFs are g...

The neocognitron network is analysed from the point of view of the contribution of the di erent layers to the nal classi cation. A variation to the neocognitron which gives improved performance is suggested. This variant combines the low level feature extraction capabilities of the initial layers with alternative classi ers such as LVQ and Class Based Means Clustering. This is shown to give per...

Content-based image retrieval (CBIR) is a new but widelyadopted method for finding images from vast and unannotated image databases. In CBIR images are indexed on the basis of low-level features, such as color, texture, and shape, that can automatically be derived from the visual content of the images. The operation of a CBIR system can be seen as a series of more or less independent processing...

We propose a novel reasoning engine for context-aware ubiquitous computing middleware in this paper. Our reasoning engine supports both rulebased reasoning and machine learning reasoning. Our main contribution is to utilize feature selection method to filter the low-level contexts which are not useful for certain special high-level context reasoning. As a result, rules and learning models in th...

Previous work on human action analysis mainly focuses on designing hand-crafted local features and combining their context information. In this paper, we propose using supervised feature learning as a way to learn spatio-temporal features. More specifically, a modified hidden conditional random field is applied to learn two high-level features conditioned on a certain action label. Among them, ...

This paper proposes a novel approach for the construction and use of multi-feature spaces in image classification. The proposed technique combines low-level descriptors and defines suitable metrics. It aims at representing and measuring similarity between semantically meaningful objects within the defined multi-feature space. The approach finds the best linear combination of predefined visual d...

In developing a visual learning method, the selection of features highly affects the performance of the method. However, the optimal features generally depend on learning tasks. Therefore, it is necessary for the effective learning to find the optimal features according to the learning task. In this paper, we propose two types of new visual learning methods; the feature combination method and t...

An efficient low-level word image representation plays a crucial role in general cursive word recognition. This paper proposes a novel representation scheme, where a word image can be represented as two sequences of feature vectors in two independent channels, which are extracted from vertical peak points on the upper external contour and at vertical minima on the lower external contour, respec...

This paper presents a novel approach to pedestrian classification which involves a high-level fusion of depth and intensity cues. Instead of utilizing depth information only in a pre-processing step, we propose to extract discriminative spatial features (gradient orientation histograms and local receptive fields) directly from (dense) depth and intensity images. Both modalities are represented ...