Local Color Histogram Research Articles

Design Patent Image Retrieval Based on Shape and Color Features

Based on the concrete characteristics and application background of design patent, according to the deficiency of the present retrieval system of design patent database, this paper proposed a synthesis design patent image retrieval method based on shape and color features. First, we present a shape retrieval approach based on the morphological description moment invariants, which can not only reflects the morphological characteristics of design patent image, but also has translation, rotation and scale invariability. Second, an improved color retrieval method based on the key local fuzzy color histogram which contains the colors’ statistic and local distributing characteristics is used to improve the color retrieval accuracy. At last, set a weight coefficient with the consideration of the similarity degree of the shape and color features. The experimental results indicated that the proposed method can retrieve similar design patent images fast and efficiently, and improve the recall ratio and precision of design patent image retrieval.

Content-based image retrieval using color and texture fused features

This paper presents a method to extract color and texture features of an image quickly for content-based image retrieval (CBIR). First, HSV color space is quantified rationally. Color histogram and texture features based on a co-occurrence matrix are extracted to form feature vectors. Then the characteristics of the global color histogram, local color histogram and texture features are compared and analyzed for CBIR. Based on these works, a CBIR system is designed using color and texture fused features by constructing weights of feature vectors. The relevant retrieval experiments show that the fused features retrieval brings better visual feeling than the single feature retrieval, which means better retrieval results.

Recognizing Cartoon Image Gestures for Retrieval and Interactive Cartoon Clip Synthesis

In this paper, we propose a new method to recognize gestures of cartoon images with two practical applications, i.e., content-based cartoon image retrieval and interactive cartoon clip synthesis. Upon analyzing the unique properties of four types of features including global color histogram, local color histogram (LCH), edge feature (EF), and motion direction feature (MDF), we propose to employ different features for different purposes and in various phases. We use EF to define a graph and then refine its local structure by LCH. Based on this graph, we adopt a transductive learning algorithm to construct local patches for each cartoon image. A spectral method is then proposed to optimize the local structure of each patch and then align these patches globally. MDF is fused with EF and LCH and a cartoon gesture space is constructed for cartoon image gesture recognition. We apply the proposed method to content-based cartoon image retrieval and interactive cartoon clip synthesis. The experiments demonstrate the effectiveness of our method.

エントロピー均等化によるパノラマ画像の横幅縮小

We describe a method for reducing the width of panoramic images with high aspect ratios on the basis of the entropy in local color histograms computed for each column in the images. We equalize the entropy for the width of a panoramic image, thereby widening the regions that have high entropy values and narrowing the regions that have low entropy values. Our experimental results show that this method can reduce the width of panoramic images more effectively and more quickly than the seam carving method presented by Avidan et al.

MULTICLASS OBJECT RECOGNITION USING CLASS-CONDITIONAL INDEPENDENT COMPONENT ANALYSIS

A new modeling technique, based on independent component analysis (ICA), is proposed to represent and recognize high-dimensional samples from a large set of classes. The model is constructed via density estimation techniques, and recognition is performed in the Bayesian decision framework. We show that the technique can be successfully used for automatic object identification in environments where a visual observer is faced with a classification problem in high-dimensional spaces with a large number of classes. A first experiment illustrates that classification using an ICA representation is a technique that, even in low dimensions, performs comparably to standard classification techniques. The second experiment tests the ICA classification model on high-dimensional data. Recognition was performed using local color histograms of images corresponding to 400 different objects. It is also shown how our approach outperforms other techniques commonly used in the context of appearance-based recognition.

Cell Histograms Versus Color Histograms for Image Representation and Retrieval

This paper presents a new approach for content-based image retrieval, which is based on the well-known and widely used color histograms. Previous approaches have used a single global color histogram (GCH) for the whole image, or local color histograms (LCHs) for cells within a grid of fixed size. Our approach is also based on a grid of cells, but unlike the latter it uses a cell histogram for each of the colors actually present in the images, representing how that color is distributed among the image cells - hence the name Cell/Color Histograms. Our experiments have shown that the actual number of colors present in images is often low. Thus we are able to achieve performance comparable to using LCHs within a grid, but with a much smaller space overhead. Furthermore, the proposed approach is very flexible in the sense that the user has alternative ways to calibrate the trade-off between space overhead and retrieval effectiveness. In fact, we have been able to outperform GCHs (typically a compact representation) in terms of effectiveness requiring less storage space.

Image retrieval based on regions of interest

Query-by-example is the most popular query model in recent content-based image retrieval (CBIR) systems. A typical query image includes relevant objects (e.g., Eiffel Tower), but also irrelevant image areas (including background). The irrelevant areas limit the effectiveness of existing CBIR systems. To overcome this limitation, the system must be able to determine similarity based on relevant regions alone. We call this class of queries region-of-interest (ROI) queries and propose a technique for processing them in a sampling-based matching framework. A new similarity model is presented and an indexing technique for this new environment is proposed. Our experimental results confirm that traditional approaches, such as Local Color Histogram and Correlogram, suffer from the involvement of irrelevant regions. Our method can handle ROI queries and provide significantly better performance. We also assessed the performance of the proposed indexing technique. The results clearly show that our retrieval procedure is effective for large image data sets.

Using an ICA representation of local color histograms for object recognition

This paper applies a Bayesian classification scheme to the problem of object recognition through probabilistic modeling of local color histograms. In this context, the density estimation is generally performed via nonparametric kernel methods and the high dimensionality does not allow precision in the results. We propose a local independent component analysis (ICA) representation of the data. Within this representation, the components can be assumed statistically independent and, for this particular problem, sparsity of the independent components is observed. We show how these two characteristics simplify and add accuracy to the density estimation and develop a Bayesian decision scheme within this representation. We propose a set of possible density estimations for supergaussian densities, the density type associated with a sparse representation. Two experiments were performed. The first one illustrates the properties of the ICA representation for local color histograms. The second experiment tests the ICA classification model for a large set of pharmaceutical products and compares this scheme with a nonparametric technique based on Gaussian Kernels, two nearest-neighbor techniques and global histogram approach.