Wyniki wyszukiwania - BazTech

1

A hybrid statistical approach for texture images classification based on scale invariant features and mixture gamma distribution

Benlakhdar Said, Rziza Mohammed, Thami Rachid Oulad Haj

Computer Methods in Materials Science

|

2020

|

Vol. 20, No. 3

95--106

EN

Image classification refers to an important process in computer vision. The purpose of this paper is to propose a novel approach named GGD-GMM and based on statistical modeling in wavelet domain to describe textured images and rely on number of principles which give its internal coherence and originality. Firstly, we propose a robust algorithm based on the combination of the wavelet transform and Scale Invariant Feature Transform. Secondly, we implement the aforementioned algorithm and fit the result using the finite mixture gamma distribution (GMM). The results, obtained for two benchmark datasets, show that the proposed algorithm has a good relevance as it provides higher classification accuracy compared to some other well known models see (Kohavi, 1995). Moreover, it shows other advantages relied to Noise-resistant and rotation invariant.

2

Robust image forgery detection using point feature analysis

William Youssef, Safwat Sherine, Abdel-Megeed Salem Mohammed

Annals of Computer Science and Information Systems

|

2019

|

Vol. 18

373–-380

EN

Day for day it becomes easier to temper digital images. Thus, people are in need of various forgery image detection. In this paper, we present forgery image detection techniques for two of the most common image tampering techniques; copy-move and splicing. We use match points technique after feature extraction process using SIFT and SURF. For splicing detection, we extracted the edges of the integral images of Y , Cb, and Cr image components. GLCM is applied for each edge integral image and the feature vector is formed. The feature vector is then fed to a SVM classifier. For the copy-move, the results show that SURF feature extraction can be more efficient than SIFT, where we achieved 80% accuracy of detecting tempered images. On the other hand, processing the image in YCbCr color model is found to give promising results in splicing image detection. We have achieved 99% true positive rate for detecting splicing images.

3

Feature extraction and template matching algorithm classification for PCB fiducial verification

Fonseka C. L. S. C., Jayasinghe J. A. K. S.

Journal of Achievements in Materials and Manufacturing Engineering

|

2018

|

Vol. 86, nr 1

14--32

EN

Purpose: Automatic Optical Inspection (AOI) systems that are extensively used in the industry of Electronics Manufacturing Services (EMS), performs the inspection of Surface Mount Devices (SMD). One of the main tasks of such an AOI system is to align a given PCB to the parameters of the corresponding PCB positioning system by a process called fiducial alignment. However, no detailed analysis has been carried out so far on the methodologies that can be used to have a very precise identification of PCB fiducial points. In our research, we have implemented an AOI system for the inspection of soldering defects of Through Hole Technology (THT) solder joints, which can be integrated to a desktop soldering robotic platform. Such platforms are used in environments where no specific lighting conditions can be provided within a surrounded atmosphere. Therefore, an AOI system that is capable of performing fiducial alignment of any given PCB under varying lighting condition is highly preferred. In this paper, we have presented a detailed analysis on feature extraction and template matching algorithms that can be used to implement a very precise fiducial verification process under normal lighting condition. Design/methodology/approach: A detailed analysis and performance evaluation have been carried out in this paper on prominent image comparison algorithms that are extensively used in the field of image processing. Findings: According to the analysis carried out in this paper, it could be observed that the combination of feature extraction and template matching algorithms gives the best performance in PCB fiducial verification process. Research limitations/implications: This paper only presents the implementation of the front end of our proposed AOI system. The implemented methodologies for the automatic identification of soldering defects will be discussed in separate research papers. Practical implications: The methodologies presented in this paper can be effectively used to implement a very precise and robust PCB fiducial verification process that can be efficiently integrated to a desktop soldering robotic system. Originality/value: This research proposes a very accurate fiducial verification process that can be used under varying lighting conditions on a wide range of different PCB fiducial points.

4

Rejestracja chmur punktów: porównanie wariantów wzajemnej rejestracji

Łępicka M. J., Kornuta T.

Pomiary Automatyka Robotyka

|

2017

|

R. 21, nr 2

5--14

PL

W dwuczęściowym artykule skupiono uwagę na problemie rejestracji chmur punktów. W pierwszej części omówiono kluczowe komponenty systemu V-SLAM uzupełnione przykładowymi algorytmami i rozwiązaniami stosowanymi w tych komponentach. W poniższej, drugiej części omówiono różne rodzaje wariantów algorytmu ICP, atrybuty punktów oraz operujące na nich metryki. Następnie omówiono metodykę badań oraz przedstawiono wyniki porównania wybranych wariantów wzajemnej rejestracji.

EN

The two-part article focuses on the problem of registration of point clouds. The first part briefly discussed the main components of V-SLAM systems and presented the main steps of the ICP (Iterative Closes Point) algorithm. In the following, second part of the paper, we analyse and compare diverse variants of the ICP algorithm. In particular, we discuss different attributes of points along with operating on them metrics that the ICP can employ. Finally, we present the research methodology and discuss the results of comparison of selected variants of ICP.

5

A binary representation for real-valued, local feature descriptors

Oszust M.

Journal of Automation Mobile Robotics and Intelligent Systems

|

2017

|

Vol. 11, No. 1

3--9

EN

The usage of real-valued, local descriptors in computer vision applications is ofen constrained by their large memory requirements and long matching time. Typical approaches to the reduction of their vectors map the descriptor space to the Hamming space in which the obtained binary strings can be efficiently stored and compared. In contrary to such techniques, the approach proposed in this paper does not require a data-driven binarisation process, but can be seen as an extension of the floating-point descriptor computation pipeline with a step that allows turning it into a binary descriptor. In this step, binary tests are performed on values determined for pixel blocks from the described image patch. In the paper, the proposed approach is described and applied to two popular real-valued descriptors, SIFT and SURF. The paper also contains a comparison of the approach with state-of-the-art binarisation techniques and popular binary descriptors. The results demonstrate that the proposed representation for real-valued descriptors outperforms other methods on four demanding benchmark image datasets.

6

Localization of component lead inside a THT solder joint for solder defects classification

Fonseka C. L. S. C., Jayasinghe J. A. K. S.

Journal of Achievements in Materials and Manufacturing Engineering

|

2017

|

Vol. 83, nr 2

57--66

EN

Purpose: Automatic Optical Inspection (AOI) systems, used in electronics industry have been primarily developed to inspect soldering defects of Surface Mount Devices (SMD) on a Printed Circuit Board (PCB). However, no commercially available AOI system exists that can be integrated to a desktop soldering robotic system, which is capable of identifying soldering defects of Through Hole Technology (THT) solder joints along with the soldering process. In our research, we have implemented an AOI platform that is capable of performing automatic quality assurance of THT solder joints in a much efficient way. In this paper, we have presented a novel approach to identify soldering defects of THT solder joints, based on the location of THT component lead top. This paper presents the methodologies that can be used to precisely identify and localize THT component lead inside a solder joint. Design/methodology/approach: We have discussed the importance of lead top localization and presented a detailed description on the methodologies that can be used to precisely segment and localize THT lead top inside the solder joint. Findings: It could be observed that the precise localization of THT lead top makes the soldering quality assurance process more accurate. A combination of template matching algorithms and colour model transformation provide the most accurate outcome in localizing the component lead top inside solder joint, according to the analysis carried out in this paper. Research limitations/implications: When the component lead top is fully covered by the soldering, the implemented methodologies will not be able to identify the actual location of it. In such a case, if the segmented and detected lead top locations are different, a decision is made based on the direction in which the solder iron tip touches the solder pad. Practical implications: The methodologies presented in this paper can be effectively used to have a precise localization of component lead top inside the solder joint. The precise identification of component lead top leads to have a very precise quality assurance capability to the implemented AOI system. Originality/value: This research proposes a novel approach to identify soldering defects of THT solder joints in a much efficient way based on the component lead top. The value of this paper is quite high, since we have taken all the possibilities that may appear on a solder joint in a practical environment.

7

Automatyczna generacja cech z wykorzystaniem anizotropowego trójwymiarowego algorytmu SIFT dla potrzeb segmentacji danych pochodzących z Tomografii Komputerowej

Skalski A., Szczotka A., Kędzierawski P., Kuszewski T., Kukołowicz P.

Przegląd Elektrotechniczny

|

2015

|

R. 91, nr 5

25-28

PL

W artykule przedstawiono algorytm, w implementacji dla trójwymiarowych danych obrazowych, generacji punktów charakterystycznych oraz wektorów cech. Algorytm wykorzystuje anizotropowe rozszerzenie algorytmu SIFT. Zaproponowana metodologia została wykorzystana do określenia właściwości separacyjnych wektorów dla potrzeb segmentacji danych tomograficznych pacjentów z nowotworem prostaty. Właściwości separacyjne zostały potwierdzone na podstawie klasyfikacji techniką gRBF SVM z wykorzystaniem sprawdzianu krzyżowego.

EN

In the paper, a 3D version of algorithm generating points and feature vectors is shown. The algorithm is based on anisotropic implementation of SIFT technique. Proposed solution was used to define separation properties of vectors in CT data segmentation context. These properties were confirmed using gRBF SVM and cross-validation.

8

Vision analysis system for autonomous landing of micro drone

Skoczylas M.

Acta Mechanica et Automatica

|

2014

|

Vol. 8, no. 4

199--203

EN

This article describes a concept of an autonomous landing system of UAV (Unmanned Aerial Vehicle). This type of device is equipped with the functionality of FPV observation (First Person View) and radio broadcasting of video or image data. The problem is performance of a system of autonomous drone landing in an area with dimensions of 1m × 1m, based on CCD camera coupled with an image transmission system connected to a base station. Captured images are scanned and landing marker is detected. For this purpose, image features detectors (such as SIFT, SURF or BRISK) are utilized to create a database of keypoints of the landing marker and in a new image keypoints are found using the same feature detector. In this paper results of a framework that allows detection of definedmarker for the purpose of drone landing field positioning will be presented.

9

Classification of animals to determine the migration potential at the construction of new infrastructure

Matuska S., Hudec R., Benco M., Zachariasova M.

Archives of Transport System Telematics

|

2013

|

Vol. 6, iss. 4

26--30

EN

At the planning and construction of new infrastructures, the information about migration potential of animals in a target area is needed. This information will be used to design of migration corridors for wild animals. To determine the migration potential of animals based on distributed video camera system, new methods for object recognition and classification are developed. In general, an object recognition system consists of three steps, namely, the image feature extraction from the training database, training the classifier and evaluation of query image of object/animal. In this paper, an extraction of local key point by SIFT or SURF descriptors, bags of key points method in combination with SVM classifier and two hybrid key points detection methods are proposed in detail.

10

Przetwarzanie obrazu pola obserwacji metodą dopasowania deskryptorów punktów kluczowych

Jakubowski J., Pacan J.

TTS Technika Transportu Szynowego

|

2012

|

R. 19, nr 9

2117--2125, CD

PL

W artykule przedstawiono wyniki wstępnych badań nad możliwością wykorzystania transformacji obrazu SIFT w zagadnieniach interpretacji treści obrazu cyfrowego. Efektem transformacji jest zbiór punktów kluczowych, których opis wyrażony 128-elementowym wektorem cech stanowi dane wejściowe dla procedury klasyfikacji minimalno-odległościowej. Prezentowany materiał omawia własności samej metody oraz ilustruje w sposób ilościowy jej zdolność do detekcji wyróżnionej klasy obiektów, których wzorce znajdują się w bazie danych.

EN

The paper presents the results of an initial research on the possibilities to use SIFT transform as a method to analyze the scene in digital images. The output of the transform is a set of key points described with a 128-element vector of features that can be used as an input to a minimum distance classifier. Presented material shows basic properties of the method as well as its quantitative assessment to detect distinguished objects of known patterns included in the data base.

11

Application of scale-invariant feature transform to fingerprint classification

Sobek J., Cetnarowicz D., Dąbrowski A.

Elektronika : konstrukcje, technologie, zastosowania

|

2012

|

Vol. 53, nr 5

40-45

EN

In this paper an application of SIFT (Scale-Invariant Feature Transform) is presented. Even though the SIFT is a computer vision algorithm, its properties confirmed by the described algorithm allow for classification of the fingerprints. The described experiment was performed using FVC2004 fingerprints database. We obtained FRR (False Rejection Ratio) of about 15% and FAR (False Acceptance Ratio) equal to 0%. This result allows for application in the access control to restricted areas, i.e., if FAR has to be Iow. In generał, SIFT can be considered as the first stage of classification of fingerprints in the database searching.

PL

Artykuł prezentuje zastosowanie algorytmu SIFT (z ang. Scale Inwariant Feature Transform - skaloniezmiennicze przekształcenie cech). Pomimo iż SIFT jest algorytmem do kojarzenia pewnych obiektów w obrazach, jego cechy pozwalają na wykorzystanie go przy klasyfikacji odcisków palców. Opisany eksperyment został przeprowadzony przy użyciu testowej bazy danych o nazwie FVC2004, która zawiera materiał daktyloskopijny. Współczynnik FRR (współczynnik błędnego odrzucenia) został uzyskany na poziomie ok. 15%, a współczynnik FAR (współczynnik błędnej akceptacji) równy 0%. Rezultaty te pozwalają stosować taki algorytm np. w systemach ochrony stref chronionych. Algorytm SIFT może być także pierwszym etapem przeszukiwania bazy danych w celu wstępnej selekcji obrazów z dużej bazy danych.

12

PCA based modification of SIFT-like methods for object class recognition

Owczarek A.

Challenges of Modern Technology

|

2011

|

Vol. 2, no. 1

23--26

EN

This paper discusses a novel PCA based modification of standard SIFT and PCA-SIFT algorithms for the purpose of object class recognition. New descriptors intended to be simultaneously distinctive enough to describe the difference between features belonging to separate categories and general enough to capture the variations among features from the same class are proposed. The experimental results, gained for a test database, showing the reliability of introduced approach are presented.

13

Śledzenie obszarów zainteresowania w sekwencjach obrazów bronchoskopowych za pomocą metody SIFT

Pawlik P., Bubliński Z., Duplaga M.

Automatyka / Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie

|

2009

|

T. 13, z. 3/1

941-947

PL

Artykuł przedstawia próbę wykorzystania zmodyfikowanej metody SIFT do śledzenia wybranych obszarów zainteresowania na sekwencjach obrazów bronchoskopowych. Opracowaną metodę przetestowano na kilkudziesięciu filmach zarejestrowanych w trakcie badań medycznych uzyskując bardzo obiecujące wyniki oraz wskazano kierunki możliwych ulepszeń.

EN

The paper presents an attempt to utilize the modified SIFT method for ROI (region of interest) tracking on sequences of bronchoscopy images. The method was tested on several movies recorded during medical treatment and very promising results were obtained. Also, the areas of possible improvements were pointed out.