Byoung Chul Ko

Object-of-interest image segmentation based on human attention and semantic region clustering

We propose a novel object-of-interest (OOI) segmentation algorithm for various images that is based on human attention and semantic region clustering. As object-based image segmentation is beyond current computer vision techniques, the proposed method segments an image into regions, which are then merged as a semantic object. At the same time, an attention window (AW) is created based on the saliency map and saliency points from an image. Within the AW, a support vector machine is used to select the salient regions, which are then clustered into the OOI using the proposed region merging. Unlike other algorithms, the proposed method allows multiple OOIs to be segmented according to the saliency map.

Automatic white blood cell segmentation using stepwise merging rules and gradient vector flow snake.

This study aims at proposing a new stained WBC (white blood cell) image segmentation method using stepwise merging rules based on mean-shift clustering and boundary removal rules with a GVF (gradient vector flow) snake. This paper proposes two different schemes for segmenting the nuclei and cytoplasm of WBCs, respectively. For nuclei segmentation, a probability map is created using a probability density function estimated from samples of WBCs nuclei and sub-images cropped to include a nucleus based on the fact that nuclei have a salient color against the background and red blood cells. Mean-shift clustering is then performed for region segmentation, and a stepwise merging scheme applied to merge particle clusters with a nucleus. Meanwhile, for cytoplasm segmentation, morphological opening is applied to a green image to boost the intensity of the granules and canny edges detected within the sub-image. The boundary edges and noise edges are then removed using removal rules, while a GVF snake is forced to deform to the cytoplasm boundary edges. When evaluated using five different types of stained WBC, the proposed algorithm produced accurate segmentation results for most WBC types.

X-ray Image Classification Using Random Forests with Local Wavelet-Based CS-Local Binary Patterns

This paper presents a fast and efficient method for classifying X-ray images using random forests with proposed local wavelet-based local binary pattern (LBP) to improve image classification performance and reduce training and testing time. Most studies on local binary patterns and its modifications, including centre symmetric LBP (CS-LBP), focus on using image pixels as descriptors. To classify X-ray images, we first extract local wavelet-based CS-LBP (WCS-LBP) descriptors from local parts of the images to describe the wavelet-based texture characteristic. Then we apply the extracted feature vector to decision trees to construct random forests, which are an ensemble of random decision trees. Using the random forests with local WCS-LBP, we classified one test image into the category having the maximum posterior probability. Compared with other feature descriptors and classifiers, the proposed method shows both improved performance and faster processing time.

Classification of Potential Water Bodies Using Landsat 8 OLI and a Combination of Two Boosted Random Forest Classifiers

This study proposes a new water body classification method using top-of-atmosphere (TOA) reflectance and water indices (WIs) of the Landsat 8 Operational Land Imager (OLI) sensor and its corresponding random forest classifiers. In this study, multispectral images from the OLI sensor are represented as TOA reflectance and WI values because a classification result using two measures is better than raw spectral images. Two types of boosted random forest (BRF) classifiers are learned using TOA reflectance and WI values, respectively, instead of the heuristic threshold or unsupervised methods. The final probability is summed linearly using the probabilities of two different BRFs to classify image pixels to water class. This study first demonstrates that the Landsat 8 OLI sensor has higher classification rate because it provides improved signal-to-ratio radiometric by using 12-bit quantization of the data instead of 8-bit as available from other sensors. In addition, we prove that the performance of the proposed combination of two BRF classifiers shows robust water body classification results, regardless of topology, river properties, and background environment.

Modeling and Formalization of Fuzzy Finite Automata for Detection of Irregular Fire Flames

Fire-flame detection using a video camera is difficult because a flame has irregular characteristics, i.e., vague shapes and color patterns. Therefore, in this paper, we propose a novel fire-flame detection method using fuzzy finite automata (FFA) with probability density functions based on visual features, thereby providing a systemic approach to handling irregularity in computational systems and the ability to handle continuous spaces by combining the capabilities of automata with fuzzy logic. First, moving regions are detected via background subtraction, and the candidate flame regions are then identified by applying flame color models. In general, flame regions have a continuous irregular pattern; therefore, probability density functions are generated for the variation in intensity, wavelet energy, and motion orientation and applied to the FFA. The proposed algorithm is successfully applied to various fire/non-fire videos, and its detection performance is better than that of other methods.

Microscopic Cell Nuclei Segmentation Based on Adaptive Attention Window

This paper presents an adaptive attention window (AAW)-based microscopic cell nuclei segmentation method. For semantic AAW detection, a luminance map is used to create an initial attention window, which is then reduced close to the size of the real region of interest (ROI) using a quad-tree. The purpose of the AAW is to facilitate background removal and reduce the ROI segmentation processing time. Region segmentation is performed within the AAW, followed by region clustering and removal to produce segmentation of only ROIs. Experimental results demonstrate that the proposed method can efficiently segment one or more ROIs and produce similar segmentation results to human perception. In future work, the proposed method will be used for supporting a region-based medical image retrieval system that can generate a combined feature vector of segmented ROIs based on extraction and patient data.

Spatiotemporal bag-of-features for early wildfire smoke detection

Wildfire smoke detection is particularly important for early warning systems, because smoke usually rises before flames arise. Therefore, this paper presents an automatic wildfire smoke detection method using computer vision and pattern recognition techniques. First, candidate blocks are identified using key-frame differences and nonparametric smoke color models to detect smoke-colored moving objects. Subsequently, three-dimensional spatiotemporal volumes are built by combining the candidate blocks in the current key-frame with the corresponding blocks in previous frames. A histogram of oriented gradient (HOG) is extracted, and a histogram of oriented optical flow (HOOF) is extracted as a temporal feature based on the fact that the direction of smoke diffusion is upward owing to thermal convection. From spatiotemporal features of training data, a visual codebook and a bag-of-features (BoF) histogram are generated using our proposed weighting scheme. For smoke verification, a random forest classifier is built during the training phase using the BoF histogram. The random forest with the BoF histogram can increase the detection accuracy performance when compared with related methods and allow smoke detection to be carried out in near real time.

Automatic medical image annotation and keyword-based image retrieval using relevance feedback

This paper presents novel multiple keywords annotation for medical images, keyword-based medical image retrieval, and relevance feedback method for image retrieval for enhancing image retrieval performance. For semantic keyword annotation, this study proposes a novel medical image classification method combining local wavelet-based center symmetric–local binary patterns with random forests. For keyword-based image retrieval, our retrieval system use the confidence score that is assigned to each annotated keyword by combining probabilities of random forests with predefined body relation graph. To overcome the limitation of keyword-based image retrieval, we combine our image retrieval system with relevance feedback mechanism based on visual feature and pattern classifier. Compared with other annotation and relevance feedback algorithms, the proposed method shows both improved annotation performance and accurate retrieval results.

X-ray image classification using Random Forests with Local Binary Patterns

This paper presents a novel algorithm for the efficient classification of X-ray images to enhance the accuracy and performance. As for describing the characteristics of X-ray image, new Local Binary Patterns (LBP) is employed that allows simple and efficient feature extraction for texture information. To achieve fast and accurate classification task, Random Forests that is decision tree based ensemble classifier is applied. Comparing with other feature descriptors and classifiers, the testing results show that the proposed method improves accuracy, especially the speed for either training or testing.

Wildfire smoke detection using temporospatial features and random forest classifiers

We propose a wildfire smoke detection algorithm that uses temporospatial visual features and an ensemble of decision trees and random forest classifiers. In general, wildfire smoke detection is particularly important for early warning systems because smoke is usually generated before flames; in addition, smoke can be detected from a long distance owing to its diffusion characteristics. In order to detect wildfire smoke using a video camera, temporospatial characteristics such as color, wavelet coefficients, motion orientation, and a histogram of oriented gradients are extracted from the preceding 100 corresponding frames and the current keyframe. Two RFs are then trained using independent temporal and spatial feature vectors. Finally, a candidate block is declared as a smoke block if the average probability of two RFs in a smoke class is maximum. The proposed algorithm was successfully applied to various wildfire-smoke and smoke-colored videos and performed better than other related algorithms.