This paper presents a novel method to grade the date fruits based on the combination of shape and texture features. The method begins with reducing the specular reflection and small noise using a bilateral filter. Threshold based segmentation is performed for background removal and fruit part selection from the given image. Shape features is extracted using the contour of the date fruit and texture features are extracted using Curvelet transform and Local Binary Pattern (LBP) from the selected date fruit region. Finally, combinations of shape and texture features are fused to grade the dates into six grades. k-Nearest Neighbour(k-NN) classifier yields the best grading rate compared to other two classifiers such as Support Vector Machine (SVM) and Linear Discriminant(LDA) classifiers. The experiment result shows that our technique achieves highest accuracy.
This paper presents a novel method to recognize stem - calyx of an apple using shape descriptors. The main drawback of existing apple grading techniques is that stem - calyx part of an apple is treated as defects, this leads to poor grading of apples. In order to overcome this drawback, we proposed an approach to recognize stem-calyx and differentiated from true defects based on shape features. Our method comprises of steps such as segmentation of apple using grow-cut method, candidate objects such as stem-calyx and small defects are detected using multi-threshold segmentation. The shape features are extracted from detected objects using Multifractal, Fourier and Radon descriptor and finally stem-calyx regions are recognized and differentiated from true defects using SVM classifier. The proposed algorithm is evaluated using experiments conducted on apple image dataset and results exhibit considerable improvement in recognition of stem-calyx region compared to other techniques.
The underwater images usually suffers from non-uniform lighting, low contrast, blur and diminished colors. In this paper, we proposed an image based preprocessing technique to enhance the quality of the underwater images. The proposed technique comprises a combination of four filters such as homomorphic filtering, wavelet denoising, bilateral filter and contrast equalization. These filters are applied sequentially on degraded underwater images. The literature survey reveals that image based preprocessing algorithms uses standard filter techniques with various combinations. For smoothing the image, the image based preprocessing algorithms uses the anisotropic filter. The main drawback of the anisotropic filter is that iterative in nature and computation time is high compared to bilateral filter. In the proposed technique, in addition to other three filters, we employ a bilateral filter for smoothing the image. The experimentation is carried out in two stages. In the first stage, we have conducted various experiments on captured images and estimated optimal parameters for bilateral filter. Similarly, optimal filter bank and optimal wavelet shrinkage function are estimated for wavelet denoising. In the second stage, we conducted the experiments using estimated optimal parameters, optimal filter bank and optimal wavelet shrinkage function for evaluating the proposed technique. We evaluated the technique using quantitative based criteria such as a gradient magnitude histogram and Peak Signal to Noise Ratio (PSNR). Further, the results are qualitatively evaluated based on edge detection results. The proposed technique enhances the quality of the underwater images and can be employed prior to apply computer vision techniques.
In this paper, we propose a novel technique to reconstruct 3D surface of an underwater object using stereo images. Reconstructing the 3D surface of an underwater object is really a challenging task due to degraded quality of underwater images. There are various reason of quality degradation of underwater images i.e., non-uniform illumination of light on the surface of objects, scattering and absorption effects. Floating particles present in underwater produces Gaussian noise on the captured underwater images which degrades the quality of images. The degraded underwater images are preprocessed by applying homomorphic, wavelet denoising and anisotropic filtering sequentially. The uncalibrated rectification technique is applied to preprocessed images to rectify the left and right images. The rectified left and right image lies on a common plane. To find the correspondence points in a left and right images, we have applied dense stereo matching technique i.e., graph cut method. Finally, we estimate the depth of images using triangulation technique. The experimental result shows that the proposed method reconstruct 3D surface of underwater objects accurately using captured underwater stereo images.