The Unmanned Aerial Vehicles (UAV) are widely used for capturing images in border area surveillance, disaster intensity monitoring, etc. An aerial photograph offers a permanent recording solution a...

/pdf/log-transform-based-optimal-image-enhancement-using-firefly-1a2ogtt1l4.pdf

Log Transform Based Optimal Image Enhancement Using Firefly Algorithm for Autonomous Mini Unmanned Aerial Vehicle: An Application of Aerial Photography

In this paper, an unsupervised segmentation methodology is proposed for remotely sensed images by using Fractional Differential FD based texture analysis model and Iterative Self-Organizing Data Analysis Technique Algorithm ISODATA. Essentially, image segmentation is used to assign unique class labels to different regions of an image. In this work, it is transformed into texture segmentation by signifying each class label as a unique texture class. The FD based texture analysis model is suggested for texture feature extraction from images and ISODATA is used for segmentation. The proposed methodology was first implemented on artificial target images and then on remote sensing images from Google Earth. The results of the proposed methodology are compared with those of the other texture analysis methods such as LBP Local Binary Pattern and NBP Neighbors based Binary Pattern by visual inspection as well as using classification measures derived from confusion matrix. It is justified that the proposed methodology outperforms LBP and NBP methods.

Unsupervised Segmentation of Remote Sensing Images using FD Based Texture Analysis Model and ISODATA

Nowadays, feature selection is considered as a de facto standard in the field of pattern recognition where high-dimensional feature attributes are used. The main purpose of any feature selection algorithm is to reduce the dimensionality of the input feature vector while improving the classification ability. Here, a Memetic Algorithm (MA)-based wrapper–filter feature selection method is applied for the recognition of handwritten word images in segmentation-free approach. In this context, two state-of-the-art feature vectors describing texture and shape of the word images, respectively, are considered for feature dimension reduction. Experimentation is conducted on handwritten Bangla word samples comprising 50 popular city names of West Bengal, a state of India. Final results confirm that for the said recognition problem, subset of features selected by MA produces increased recognition accuracy than the individual feature vector or their combination when applied entirely.

Feature Selection for Handwritten Word Recognition Using Memetic Algorithm

This paper presents a supervised feature learning method to learn discriminative and compact descriptors for drusen segmentation from retinal images. This method combines generalized low rank approximation of matrices with supervised manifold regularization to learn new features from image patches sampled from retinal images. The learned features are closely related to drusen and potentially free from information that is redundant in distinguishing drusen from background. The learned feature representations are then vectorized and used to train a support vector machine (SVM) classifier. Finally, the obtained SVM classifier is employed to classify the pixels in the test images as drusen or non-drusen. The performance of the proposed method is validated on the STARE and DRIVE databases, where it achieves an average sensitivity/specificity/accuracy of 90.03%/97.06%/96.92% and of 87.41%/94.93%/94.81%, respectively. We also experimentally compare the proposed method with the several representative state-of-the-art drusen segmentation techniques and find that it generates superior accuracy.

Drusen Segmentation From Retinal Images via Supervised Feature Learning

In medical imaging, positron emission tomography (PET) shows metabolic changes of an organism in pseudo color and magnetic resonance (MR) imaging presents anatomical structures in gray level. The PET and MR brain medical image fusion produces one composite image rendering the anatomical structures with metabolic changes to help doctors effectively diagnose a possible disease. For this purpose, a new fusion method based on Intensity-Hue-Saturation model and log-Gabor wavelet transform is proposed. First, MR image and the intensity component of PET image are decomposed by log-Gabor wavelet transform with suitable decomposition scale. Then, maximum selection’ fusion rule for the high-frequency sub-band and two-stage fusion rule based on weighted-averaging scheme and visibility measure for the low-frequency sub-band are employed. Finally, a new intensity component, obtained by applying reverse log-Gabor wavelet transform to the fused high-and low-frequency sub-bands, along with original hue and saturation components of PET image are converted to obtain our fused color image. In our fused images, both anatomical structures and color changes are rendered with effectively-reduced color distortion. Experimental results on twelve sets, including normal axial, normal coronal, and Alzheimer’s disease brain images, demonstrate that our fusion method outpaces framelet-transform-based method both visually and quantitatively.

Fusion of PET and MR Brain Images Based on IHS and Log-Gabor Transforms

This paper is dedicated to the modelling of textured images influenced by fractional derivatives for texture detection. As most of the images contain textures, texture analysis becomes the most important for image understanding and it is a key solution for many computer vision applications. Hence, texture must be suitably detected and represented. Nevertheless, existing texture detection algorithms consider texture as a unique feature from edges. The proposed model explores a novel way of developing texture detection algorithm by mimicking edge detection algorithms. The method assumes that texture feature is analogous to edges and thus, the time complexity is reduced significantly. The model proposed in this work is based on Gaussian kernel smoothing, Fractional partial derivatives and a statistical approach. It is justified to be robust to noisy images and possesses statistical interpretation. The model is validated by the classification experiments on different types of textured images from Brodatz album. It achieves higher classification accuracy than the existing methods.

A Computational Model for Texture Analysis in Images with Fractional Differential Filter for Texture Detection

G-L fractional differential operator modified using auto-correlation function: Texture enhancement in images

The early detection of diseases such as brain tumor and lung cancer is achieved through segmenting these images. As these images are typified to contain obscure structures, a precise segmentation method needs to be evolved. The principal idea is to devise an unsupervised segmentation technique for medical images involving a partial fractional derivative (PFD)-dependent texture extraction model and an unsupervised clustering algorithm. Basically, image segmentation process allocates different tags to diverse image regions. In this chapter, the process is considered to be texture-based segmentation by representing every tag with an exclusive texture label. The textural features are extorted using PFD-based model. The ISODATA clustering is suggested for segmentation through pixel-based classification. This process is experimented on different test cases such as images of lung cancer detection and brain tumor detection and is able to produce higher accuracy than existing methods.

S. Hemalatha

Papers

Unsupervised Segmentation of Remote Sensing Images using FD Based Texture Analysis Model and ISODATA

A Computational Model for Texture Analysis in Images with Fractional Differential Filter for Texture Detection

G-L fractional differential operator modified using auto-correlation function: Texture enhancement in images

Partial Fractional Derivative (PFD) based Texture Analysis Model for Medical Image Segmentation