A library usually holds thousands of books and each book is assigned to a unique position so that the visitors can find the books easily by checking the database of the library. However, the misplaced books bring troubles for readers to find them. Therefore, finding out these misplaced books and rearranging them is one of the important jobs for librarians. In this paper, a convolutional-neural-network-based book label recognition algorithm is proposed to help librarians finding out the misplaced books by scanning the book labels. The algorithm is divided into two parts: the first part applies image processing techniques to extract the characters of the labels attached to each book from the images of the bookshelves. The second part uses convolutional neural networks (CNNs) to train a classifier for recognizing characters. In this part, a CNN with four convolutional layers is designed to train classifiers for classifying characters and numbers that are used for the recognition of the text.
This paper proposes an algorithm for book segmentation based on bookshelves images. The algorithm can be separated into three parts. The first part is pre-processing, aiming at eliminating or decreasing the effect of image noise and illumination conditions. The second part is near-horizontal line detection based on Canny edge detector, and separating a bookshelves image into multiple sub-images so that each sub-image contains an individual shelf. The last part is book segmentation. In each shelf image, near-vertical line is detected, and obtained lines are used for book segmentation. The proposed algorithm was tested with the bookshelf images taken from OPIE library in MTU, and the experimental results demonstrate good performance.
This paper studies bruise detection in apples using 3-D imaging. Bruise detection based on 3-D imaging overcomes many limitations of bruise detection based on 2-D imaging, such as low accuracy, sensitive to light condition, and so on. In this paper, apple bruise detection is divided into two parts: feature extraction and classification. For feature extraction, we use a framework that can directly extract local binary patterns from mesh data. For classification, we studies support vector machine. Bruise detection using 3-D imaging is compared with bruise detection using 2-D imaging. 10-fold cross validation is used to evaluate the performance of the two systems. Experimental results show that bruise detection using 3-D imaging can achieve better classification accuracy than bruise detection based on 2-D imaging.
We propose a cluster-driven trilateral filter for speckle reduction in ultrasound images. In addition to operating in the spatial dimension and the intensity dimension, the proposed filter also merges clustering information simultaneously. We compare the proposed filter with a normalized bilateral filter for speckle reduction using real 3-D ultrasound images. Our experimental results indicate that the cluster-driven trilateral filter exhibits better performance for speckle reduction and edge feature preservation than the normalized bilateral filter. In addition, we investigate the graphic processing unit (GPU) technique and apply it to the proposed 3-D filter. We design and test a GPU framework and compare it with a single-core CPU framework. Our experimental results show that the GPU-accelerated trilateral filter can obtain a roughly 20-fold increase in speed.
In this paper, we propose a mobile system for aiding doctors in skin cancer diagnosis and other persons in skin cancer
monitoring. The basic idea is to use image retrieval techniques to help the users to find the similar skin cancer cases
stored in a database by using smart phones. The query image can be taken by a smart phone from a patient or can be
uploaded from other resources. The shapes of the skin lesions are used for matching two skin lesions, which are
segmented from skin images using the skin lesion extraction method developed in 1. The features used in the proposed
system are obtained by Fourier descriptor. A prototype application has been developed and can be installed in an iPhone.
In this application, the iPhone users can use the iPhone as a diagnosis tool to find the potential skin lesions in a persons’
skin and compare the skin lesions detected by the iPhone with the skin lesions stored in a database in a remote server.
In this paper, we study image enhancement technologies for stereoscopic images and an image enhancement algorithm
using salient features and wavelet transform is proposed. In the proposed algorithm, the stereoscopic images are
decomposed into different subbands and wavelet coefficients are modified based on salient features. Objective and
subjective tests were performed to verify the effectiveness of the proposed algorithm. The experimental results show that
the proposed algorithm outperforms some conventional algorithms and has great potential in the enhancement of
Saccadic eyes are important human behaviors and have important applications in commercial and security fields. In this
paper, we focus on saccadic eyes recognition from 3-D shape data acquired from a 3-D near infrared sensor. Two salient
features, normal vectors of meshes and curvatures of surfaces, are extracted. The distributions of normal vectors and
curvatures are computed to represent eye states. The support vector machine (SVM) is applied to classify eyes states into
saccadic and non-saccadic eyes states. To verify the proposed method, we performed three groups of experiments using
different strategies for samples selected from 300 3-D data, and present experimental results that demonstrate the
effectiveness and robustness of the proposed algorithm.
In this paper, we develop an auto-focus algorithm using a new sharpness function. Different from other sharpness
functions used for auto-focusing in the past, the new defined sharpness function is more robust to noise, jitter of the
camera. In order to test the algorithm, a modified hill climbing algorithm is used in the experiments to find the focused
lens position and the experimental results show that the new auto-focus algorithm based on the new sharpness function
has better performance.
Current DCT based image enhancement techniques will produce heavy artifacts when the enhancement factors are
increased. In order to attack this issue, in this paper, we develop a new image enhancement algorithm in the DCT domain
for radiologists to screen mammograms. In the proposed algorithm, with a given target contrast value and visual quality
requirement, genetic algorithm is used to search the optimal parameter setting for image enhancement. The new image
enhancement algorithm can reduce the artifact introduced by the enhancement effectively. Both objective test and
subjective test were used to verify the proposed algorithm. The experimental results show that the enhanced images have
reduced artifacts and better visual quality.
A new speckle reduction method for ultrasonic images is presented. The proposed approach exploits the knowledge of
multiplicative speckle model and a regularization scheme is applied to diffusion processing. The nonlinear diffusion is
integrated with dyadic wavelet transform. Experimental results show the new algorithm can not only reduce speckle
effectively, but also preserve and even enhance edge and details.
In this paper, we study speckle reduction technology for 3-D ultrasound images and a 3-D anisotropic diffusion (AD)
filter is developed. The 3-D anisotropic diffusion filter works directly in the 3-D image domain and can overcome the
limitations of the 2-D anisotropic diffusion filter and the traditional 3-D anisotropic diffusion filter. The proposed
algorithm uses normalized gradient to replace gradient in the computation of the diffusion coefficients, which can reduce
the speckle effectively while preserving the edges. Experiments have been performed on real 3-D ultrasound images and
the experimental results show the effectiveness of the proposed 3D anisotropic diffusion filter.