Professional Documents
Culture Documents
Sc |
IEEE
REAL TIME PROJECTS& TRAINING GUIDE
SOFTWARE & EMBEDDED
www.makefinalyearproject.com
IGTMA02 TITLE: Optic Disk Detection in Fundus Image Based on Structured Learning
IGTMA03 TITLE: Color Balance and Fusion for Underwater Image Enhancement
IGTMA07 TITLE: The Simple Image Processing Scheme for Document Retrieval Using
Date of Issue as Query
IGTMA10 TITLE: Learning a Deep Single Image Contrast Enhancer from Multi-Exposure
Images
Abstract—Due to the poor lighting condition and limited dynamic range of digital
imaging devices, the recorded images are often under-/over-exposed and with low
contrast. Most of previous single image contrast enhancement (SICE) methods adjust
the tone curve to correct the contrast of an input image. Those methods, however, often
fail in revealing image details because of the limited information in a single image. On
the other hand, the SICE task can be better accomplished if we can learn extra
information from appropriately collected training data. In this paper, we propose to use
the convolutional neural network (CNN) to train a SICE enhancer. One key issue is
how to construct a training data set of low-contrast and high-contrast image pairs for
end-to-end CNN learning. To this end, we build a large-scale multi-exposure image
data set, which contains 589 elaborately selected high-resolution multi-exposure
sequences with 4,413 images. Thirteen representative multi-exposure image fusion and
stack-based high dynamic range imaging algorithms are employed to generate the
contrast enhanced images for each sequence, and subjective experiments are conducted
to screen the best quality one as the reference image of each scene. With the
constructed data set, a CNN can be easily trained as the SICE enhancer to improve the
contrast of an under-/over-exposure image. Experimental results demonstrate the
advantages of our method over existing SICE methods with a significant margin.
This paper deals with the colorization-based image coding algorithm. In this algorithm,
a color image is compressed by encoding its luminance image by standard coding
method such as JPEG coding and by storing several color pixels called as
representative pixels (RPs). In decoding phase, a color image is restored from
luminance image and color information of RPs using the image colorization technique.
While previous studies have achieved a high coding performance, the compression
method of RPs has not been considered because the positions of RPs are
inhomogeneous. In order to improve the image coding performance, this paper
proposes the RPs compression algorithm using the graph Fourier transform. Numerical
results show that proposed algorithm achieves better performance than JPEG2000
coding.
Image blurring is one of the most important concerns which modest the quality of
image. Image blurring can have occurred due to many different reasons. Image de-
blurring play a big area as a task for researchers to come over this challenge. There are
many methods developed for image processing to go over image blurring issue.
However, in this paper a new filter is suggested to merge with other de-blurring
methods for improving image de-blurring enhancement. The proposed filter based on
combining Markov basis and Laplace filter, it is slightly modified to make it
appropriate for color image. Escalation image edge content is one of the proposed filter
using. Moreover, merge the proposed filter with other de-blurring algorithms provides
high quality outcomes to improve the performance of several de-blurring procedures.
Also, by using median filter the outcomes can be rise up for both color and gray images.
The proposed filter compared with other filters and gives promised results.
Coronary calcium causes beam hardening and blooming artifacts on cardiac computed
tomography angiography (CTA) images, which lead to overestimation of lumen
stenosis and reduction of diagnostic specificity. To properly remove coronary
calcification and restore arterial lumen precisely, we propose a machine learning-based
method with a multi-step in painting process. We developed a new network
configuration, Dense-Unet, to achieve optimal performance with low computational
cost. Results after the calcium removal process were validated by comparing with gold-
standard X-ray angiography. Our results demonstrated that removing coronary
calcification from images with the proposed approach was feasible, and may
potentially improve the diagnostic accuracy of CTA.
IGTMA16 TITLE: Quality Assessment of Thai Rice Kernels Using Low Cost Digital Image
Processing System
Abstract—This paper presents a low cost digital image processing system for quality
assessment of Thai rice kernels. Nowadays, Thailand is the top country which export
rice into the world market, according to the mention of the Rice Trader, the export
volume is 9,883,288 tons in 2016 and export value is 154,434 million baht or 4,401
million dollars.Thai rice quality is controlled by rice department, ministry of commerce
Thailand in order to guarantee the quality in market including prices base on grade of
rice quality. Thence, quality assessment of Thai rice kernels is required. Quality
assessment or grading of Thai rice kernels usually use manual operation by person in
cooperating with equipment called micrometer to measure geometrical features such
as length, width, and area of rice kernels. This method takes a long time and also gives
uncertainty in results due to eye fatigue because size of rice kernels is very small.
Therefore, an image processing technique is then applied to measure size of Thai rice
kernels. Proposed system consists of flatbed scanner and image processing algorithm
which correspond to measure of Thai rice kernels. The low cost system for quality
assessment of Thai rice kernels can be delivered to Thai rice industry, the certainty of
results and speed of quality assessment can be significantly improved.
Abstract— With the development of web-based technologies, it has been observed that
the number of software called “bot” in the Internet tends to increase. As a result of this
increase, the internet sites have become unable to use the resources in their hands
efficiently. In this study, CAPTCHA (Completely Automated Public Turing test to tell
Computers and Humans Apart) test, which is proposed to prevent bot software, was
created and solved using image processing techniques. In this context, sample texts
were created and the letters were analyzed. Performance analyses were carried out with
experimental results. As a result of the tests performed, it has been observed that the
tests performed with the template matching method can be resolved at a satisfactory
level of accuracy. In addition, it has been found that the resolution rates decrease
significantly with the addition of geometric distortions to the test texts.
IGTMA20 TITLE: Segmentation of the Main Structures in Hematoxylin and Eosin Images
IGTMA22 TITLE: The Indian Spontaneous Expression Database for Emotion Recognition
IGTMA23 TITLE: Face Antispoofing Using Speeded-Up Robust Features and Fisher Vector
Encoding
IGTMA27 TITLE: Automatic Detection of Red Light Running Using Vehicular Cameras
Abstract — The red traffic light running is a very common traffic violation. Nowadays,
vehicles running red traffic lights are detected by sensors fixed on the streets. However
a very small percentage of all traffic lights are equipped with such sensors. For this
reason, this work proposes a red light runner detection to be performed by a system
that consists of a camera and a computer embedded in the vehicle. An algorithm is also
proposed to process the recorded videos and a prototype was implemented. The
prototype's goal is to monitor work vehicles without any intervention in driving, acting
only in as an educational tool. Tests are performed with video recorded in the streets
of Belo Horizonte during the day and with a benchmark video using the implemented
prototype. The results are compared based on the execution time and accuracy. The
video processing took less one tenth of the video duration and the accuracy was about
95.8%.
IGTMA28 TITLE: A Hierarchical Approach for Rain or Snow Removing in a Single Color
Image
Abstract—In this paper, we propose an efficient algorithm to remove rain or snow from
a single color image. Our algorithm takes advantage of two popular techniques
employed in image processing, namely, image decomposition and dictionary learning.
At first, a combination of rain/snow detection and a guided filter is used to decompose
the input image into a complementary pair: 1) the low-frequency part that is free of
rain or snow almost completely and 2) the high-frequency part that contains not only
the rain/snow component but also some or even many details of the image. Then, we
focus on the extraction of image’s details from the high-frequency part. To this end,
we design a 3-layer hierarchical scheme. In the first layer, an over complete dictionary
is trained and three classifications are carried out to classify the high-frequency part
into rain/snow and nonrain/ snow components in which some common characteristics
of rain/snow have been utilized. In the second layer, another combination of rain/snow
detection and guided filtering is performed on the rain/snow component obtained in
the first layer. In the third layer, the sensitivity of variance across color channels is
computed to enhance the visual quality of rain/snow-removed image. The effectiveness
of our algorithm is verified through both subjective (the visual quality) and objective
(through rendering rain/snow on some ground-truth images) approaches, which shows
a superiority over several state-of-the-art works.
IGTMA29 TITLE: Unconstrained Facial Beauty Prediction Based on Multi-scale K-Means∗
∗
IGTMA30 TITLE: Context-Aware Local Binary Feature Learning for Face Recognition
Abstract—In this paper, we propose a context-aware local binary feature learning (CA-
LBFL) method for face recognition. Unlike existing learning-based local face
descriptors such as discriminant face descriptor (DFD) and compact binary face
descriptor (CBFD) which learn each feature code individually, our CA-LBFL exploits
the contextual information of adjacent bits by constraining the number of shifts from
different binary bits, so that more robust information can be exploited for face
representation. Given a face image, we first extract pixel difference vectors (PDV) in
local patches, and learn a discriminative mapping in an unsupervised manner to project
each pixel difference vector into a context-aware binary vector. Then, we perform
clustering on the learned binary codes to construct a codebook, and extract a histogram
feature for each face image with the learned codebook as the final representation. In
order to exploit local information from different scales, we propose a context-aware
local binary multi-scale feature learning (CA-LBMFL) method to jointly learn multiple
projection matrices for face representation. To make the proposed methods applicable
for heterogeneous face recognition, we present a coupled CA-LBFL (C-CA-LBFL)
method and a coupled CA-LBMFL (C-CA-LBMFL) method to reduce the modality
gap of corresponding heterogeneous faces in the feature level, respectively. Extensive
experimental results on four widely used face datasets clearly show that our methods
outperform most state-of-the-art face descriptors.
Partners Address:
RAJAJINAGAR: JAYANAGAR:
#531, 63rd Cross, No 346/17, Manandi Court,
12th Main, after sevabhai hospital, 3rd Floor, 27th Cross,
5th Block, Rajajinagar, Jayanagar 3rd Block East,
Bangalore-10. Bangalore - 560011,
Landmark: Near Bashyam circle. Landmark: Near BDA Complex.