• Corpus ID: 738377

Image Categorization and Semantic Segmentation using Scale-Optimized Textons

  title={Image Categorization and Semantic Segmentation using Scale-Optimized Textons},
  author={Yousun Kang},
In computer vision research, a texton is a representative dense visual word for the bag-of-keypoints method. It has proven its effectiveness in categorizing materials and in generic object classes. Despite its success and popularity, no report describes a study that has tackled the problem of its scale optimization for given image data and associated object categories. We propose scale-optimized textons to learn the best scale for each object in a scene. We incorporate them into image… 
Malware Analysis Using Visualized Image Matrices
A novel malware visual analysis method that contains not only a visualization method to convert binary files into images, but also a similarity calculation method between these images that generates RGB-colored pixels on image matrices using the opcode sequences extracted from malware samples and calculates the similarities for the imageMatrices.
Hand Gesture and Character Recognition Based on Kinect Sensor
The purpose of this research was to see if Kinect sensor can recognize numeric and alphabetic characters written with the hand in the air, and it takes some time to master them both.


Semantic texton forests for image categorization and segmentation
The proposed semantic texton forests are ensembles of decision trees that act directly on image pixels, and therefore do not need the expensive computation of filter-bank responses or local descriptors, and give at least a five-fold increase in execution speed.
TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context
A new approach for learning a discriminative model of object classes, incorporating texture, layout, and context information efficiently, which gives competitive and visually pleasing results for objects that are highly textured, highly structured, and even articulated.
Image Categorization Using Scene-Context Scale Based on Random Forests
This paper trains multi-scale texton forests which efficiently provide both a hierarchical clustering into semantic textons and local classification in various scale levels and uses random forests, which are ensembles of randomized decision trees for image categorization.
Semantic Segmentation and Object Recognition Using Scene-Context Scale
This paper presents semantic segmentation and object recognition using scene-context scale, which means the effective region size of local context to classify an image pixel in a scene, and combines the classified category distributions of scene- context scale with the bag-of-textons model.
TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation
A new approach to learning a discriminative model of object classes, incorporating appearance, shape and context information efficiently, is proposed, which is used for automatic visual recognition and semantic segmentation of photographs.
Object categorization by learned universal visual dictionary
An optimally compact visual dictionary is learned by pair-wise merging of visual words from an initially large dictionary, and a novel statistical measure of discrimination is proposed which is optimized by each merge operation.
A Multi-Scale Learning Framework for Visual Categorization
This work proposes a Multiple Scale Learning (MSL) framework to learn the best weights for each scale in the pyramid, which would produce class-specific spatial pyramid image representations and thus provide improved recognition performance.
Image Classification using Random Forests and Ferns
It is shown that selecting the ROI adds about 5% to the performance and, together with the other improvements, the result is about a 10% improvement over the state of the art for Caltech-256.
Spatial Hierarchy of Textons Distributions for Scene Classification
Experimental tests show that the proposed approach to recognize scene categories using bags of visual words obtained hierarchically partitioning into subregion the input images achieves good performances with respect to the state of the art methods.
Sampling Strategies for Bag-of-Features Image Classification
It is shown experimentally that for a representative selection of commonly used test databases and for moderate to large numbers of samples, random sampling gives equal or better classifiers than the sophisticated multiscale interest operators that are in common use.