Türkan, Mehmet

Profile Picture
Profile URL
https://hdl.handle.net/20.500.14365/7470
Name Variants
Turkan, Mehmet
Turkan, M
Türkan, M
Job Title
Email Address
mehmet.turkan@ieu.edu.tr
mehmet.turkan@gmail.com
Main Affiliation
05.05. Computer Engineering
Status
Current Staff
Website
https://people.ieu.edu.tr/en/mehmetturkan/main
ORCID ID
0000-0002-9780-9249
Scopus Author ID
57219464962
Turkish CoHE Profile ID
5C52CF182A0545C7
Google Scholar ID
RW7hyy4AAAAJ
WoS Researcher ID
AGQ-8084-2022
Files
1739380422485.jpg (85.19 KB)

Sustainable Development Goals

NO POVERTY1
NO POVERTY
0
Research Products
ZERO HUNGER2
ZERO HUNGER
0
Research Products
GOOD HEALTH AND WELL-BEING3
GOOD HEALTH AND WELL-BEING
8
Research Products
QUALITY EDUCATION4
QUALITY EDUCATION
1
Research Products
GENDER EQUALITY5
GENDER EQUALITY
0
Research Products
CLEAN WATER AND SANITATION6
CLEAN WATER AND SANITATION
0
Research Products
AFFORDABLE AND CLEAN ENERGY7
AFFORDABLE AND CLEAN ENERGY
0
Research Products
DECENT WORK AND ECONOMIC GROWTH8
DECENT WORK AND ECONOMIC GROWTH
0
Research Products
INDUSTRY, INNOVATION AND INFRASTRUCTURE9
INDUSTRY, INNOVATION AND INFRASTRUCTURE
4
Research Products
REDUCED INEQUALITIES10
REDUCED INEQUALITIES
0
Research Products
SUSTAINABLE CITIES AND COMMUNITIES11
SUSTAINABLE CITIES AND COMMUNITIES
0
Research Products
RESPONSIBLE CONSUMPTION AND PRODUCTION12
RESPONSIBLE CONSUMPTION AND PRODUCTION
0
Research Products
CLIMATE ACTION13
CLIMATE ACTION
0
Research Products
LIFE BELOW WATER14
LIFE BELOW WATER
0
Research Products
LIFE ON LAND15
LIFE ON LAND
0
Research Products
PEACE, JUSTICE AND STRONG INSTITUTIONS16
PEACE, JUSTICE AND STRONG INSTITUTIONS
0
Research Products
PARTNERSHIPS FOR THE GOALS17
PARTNERSHIPS FOR THE GOALS
0
Research Products
Documents

55

Citations

968

h-index

15

Go to Scopus profile
Documents

47

Citations

617

Go to WoS profile
Scholarly Output

53

Articles

13

Views / Downloads

36/123

Supervised MSc Theses

9

Supervised PhD Theses

2

WoS Citation Count

463

Scopus Citation Count

721

Patents

0

Projects

0

WoS Citations per Publication

8.74

Scopus Citations per Publication

13.60

Open Access Source

17

Supervised Theses

11

JournalCount
2022 Medıcal Technologıes Congress (Tıptekno'22)4
Sıgnal Processıng4
Proceedings - International Conference on Image Processing, ICIP3
2024 Medical Technologies Congress -- OCT 10-12, 2024 -- Bodrum, TURKIYE2
Proceedings - 2020 Innovations in Intelligent Systems and Applications Conference, ASYU 20202
Current Page: 1 / 6

Scopus Quartile Distribution

Competency Cloud

GCRIS Competency Cloud

Filters

2015 - 2019112020 - 202542
Reset filters

Settings

Scholarly Output Search Results

Now showing 1 - 10 of 53
  • Thumbnail Image
    Conference Object
    Dermoscopic Lesion Segmentation Via Optimal Color Channel Fusion
    (IEEE, 2024) Okur, Erdem; Unay, Devrim; Turkan, Mehmet
    Death caused by various kinds of cancer is on rise and skin cancer is one of the most common one worldwide. Due to the importance of early detection, dermoscopy is adopted for visualizing skin lesions and computer-aided detection benefits from these dermoscopic images for better diagnosis results. One of the most important phase of automated skin lesion detection or classification is segmentation, but it is a very challenging task because of several artifacts existing on these images. In this paper, a new method to improve skin lesion segmentation from the existing deep network architectures is proposed, based on the fusion of various results produced by existing models on different color channels. Experimental validations demonstrate that the proposed method increases the average accuracy, on lesion segmentation in terms of Sorensen-Dice and Jaccard indices, when compared to conventional techniques.
  • Thumbnail Image
    Conference Object
    Citation - WoS: 1
    Citation - Scopus: 1
    Dictionary Learning With Residual Codes
    (Institute of Electrical and Electronics Engineers Inc., 2017) Oktar Y.; Türkan, Mehmet
    In conventional sparse representations based dictionary learning algorithms, initial dictionaries are generally assumed to be proper representatives of the system at hand. However, this may not be the case, especially in some systems restricted to random initialization. Therefore, a supposedly optimal state-update based on such an improper model might lead to undesired effects that will be conveyed to successive learning iterations. In this paper, we propose a dictionary learning method which includes a general error-correction process that codes the residual left over from a less intensive initial learning attempt and then adjusts the sparse codes accordingly. Experimental observations show that such additional step vastly improves rates of convergence in high-dimensional cases, also results in better converged states in the case of random initialization. Improvements also scale up with more lenient sparsity constraints. © 2017 IEEE.
  • Thumbnail Image
    Article
    Citation - WoS: 25
    Citation - Scopus: 32
    Ghosting-Free Multi-Exposure Image Fusion for Static and Dynamic Scenes
    (Elsevier, 2023) Ulucan, Oguzhan; Ulucan, Diclehan; Turkan, Mehmet
    The visual system enables humans to perceive all details of the real-world with vivid colors, while high dynamic range (HDR) technology aims at capturing natural scenes in a closer way to human perception through a large dynamic range of color gamut. Especially for traditional -low dynamic range (LDR)- de-vices, HDR-like image generation is an attractive research topic. Blending a stack of input LDR exposures is called multi-exposure image fusion (MEF). MEF is indeed a very challenging problem and it is highly prone to halo effects or ghosting and motion blur in the cases when there are spatial discontinuities in between input exposures. To overcome these artifacts, MEF keeps the best quality regions of each exposure via a weight characterization scheme. This paper proposes an effective weight map extraction framework which relies on principal component analysis, adaptive well-exposedness and saliency maps. The characterized maps are later refined by a guided filter and a blended output image is obtained via pyramidal decomposition. Comprehensive experiments and comparisons demonstrate that the developed algorithm generates very strong statistical and visual results for both static and dynamic scenes. In ad-dition, the designed method is successfully applied to the visible-infrared image fusion problem without any further optimization.(c) 2022 Elsevier B.V. All rights reserved.
  • Thumbnail Image
    Conference Object
    Vision-Based Denim Quality Assessment
    (Institute of Electrical and Electronics Engineers Inc., 2023) Balkaya, P.; Basut, M.C.; Türkan, Mehmet
    Manual color quality control is a slow process in textile industry. The color separation of denim products is judged by human operators to decide the correct chemical process to be applied such as ozone washing, to obtain the desired colors and textural characteristics for end-users. This paper aims at designing a vision-based automated system for grouping industrial denim jeans in order to eliminate human error or any other external factor, and increase efficiency and reliability of the process. Firstly, uniquely identifying features are extracted from images of the products taken in similar conditions using an image capture system, that is specifically designed for it, then parameters of clustering algorithms such as the number of clusters are decided by considering different validity scores. Finally, using the outcomes of several algorithms, a clustering is made from a batch of denim products and then the results are sent to human operators to be evaluated. © 2023 IEEE.
  • Thumbnail Image
    Master Thesis
    Hücre Sayım Uygulamaları için Akıllı Telefon Tabanlı Otomatize Opto-Akışkan Platform
    (2025) Avcı, Meryem Beyza; Türkan, Mehmet
    Hücre analiz teknolojileri, hücre canlılığı, yoğunluğu ve konfluens gibi temel parametrelerin yüksek doğrulukta değerlendirilmesini sağlayarak biyomedikal araştırmalarda önemli bir rol oynamaktadır. Gelişmiş ticari çözümlerin mevcudiyetine rağmen, birçok sistem yüksek maliyetler, karmaşık donanım gereksinimleri ve çeşitli deneysel ortamlarda kısıtlı uyarlanabilirlik nedeniyle sınırlı kalmaktadır. Bu sınırlamalara çözüm bulmak için; düşük maliyetli optik bileşenleri, otomatik sıvı yönetimini ve uyarlanabilir görüntü işleme algoritmalarını entegre eden, akıllı telefon tabanlı otomatik bir optoakışkan platform geliştirilmiştir. Platformun tasarımı, sade bir donanım yapısıyla güçlü analiz kabiliyetlerini birleştirmektedir. Sistem, hem tek kullanımlık hem de çok kullanımlık modları destekleyen temizlenebilir bir akış haznesi içermekte olup maliyet etkinliği ve esneklik sağlamaktadır. Platforma özel olarak geliştirilen mobil uygulama Qtouch; gerçek zamanlı donanım kontrolü, Bluetooth destekli iletişim ve sunucu tabanlı görüntü işlemeyi entegre ederek işlemleri kolaylaştırmaktadır. Görüntü işleme süreci, çoklu pozlama birleştirme, uyarlanabilir eşikleme ve morfolojik filtreleme teknikleri ile ham görüntü verilerini geliştirmektedir. Bu aşamalar, hücre morfolojisi veya kümelenme durumundan bağımsız olarak hücrelerin doğru şekilde bölütlenmesini sağlamakta ve derin öğrenme modellerine ya da önceden tanımlanmış parametrelere olan gereksinimi ortadan kaldırmaktadır. Farklı hücre tipleriyle gerçekleştirilen doğrulama deneyleri, platformun hücre sayımında yüksek doğruluk sağladığını ortaya koymuş; sonuçların, hücre analizinde altın standart olarak kabul edilen akış sitometrisine göre %5'ten daha az sapma gösterdiği belirlenmiştir. Platform, yüksek verimli uygulamalara uyum sağlayabilecek kapasitede olup her bir testte 10.000'den fazla hücreyi işleyebilmekte ve istatistiksel varyasyonu en aza indirmektedir. Platform, uygun maliyetli, uyarlanabilir ve yüksek doğrulukta bir çözüm sunarak ileri düzey laboratuvar sistemleri ile kaynağı kısıtlı araştırma ortamları arasında etkili bir geçiş sağlamaktadır.
  • Thumbnail Image
    Conference Object
    Citation - WoS: 3
    Citation - Scopus: 4
    Image Fusion Through Linear Embeddings
    (IEEE, 2021) Ulucan, Oguzhan; Karakaya, Diclehan; Turkan, Mehmet
    This paper proposes an effective technique for multi-exposure image fusion and visible-infrared image fusion problems. Multi-exposure fusion algorithms generally extract faulty weight maps when the input stack contains multiple and/or severely over-exposed images. To overcome this issue, an alternative method is developed for weight map characterization and refinement in addition to the perspectives of linear embeddings of images and adaptive morphological masking. This framework has then been extended to the visible and infrared image fusion problem. The comprehensive experimental comparisons demonstrate that the proposed algorithm significantly enhances the fused image quality both statistically and visually.
  • Thumbnail Image
    Conference Object
    Citation - Scopus: 1
    Patch Enhancement for Melanoma Detection With Bag of Visual Words
    (IEEE, 2022) Okur, Erdem; Turkan, Mehmet
    Melanoma is a type of skin cancer caused by the ultraviolet radiation of Sun. Melanoma will become severe if it is not detected early, and it may spread to other body organs, most commonly the lungs, brain, liver, and bones. Dermatologists look for tell-tale signs of melanoma on pigmented skin lesions (moles) to detect it or, in some cases, differentiate it from other skin diseases. Unfortunately, imprecise subjective analysis may result in a series of biopsies that are unnecessary. Furthermore, this type of imprecision may allow a melanoma case to spread undetected. This study develops an automatic melanoma detection system to overcome this challenge. The proposed method is based on Bag of Visual Words (BoVW) with a new patch enhancement scheme, which incorporates both traditional and cutting-edge methods. Experimental comparisons between the proposed method and the well-known convolutional neural network models demonstrate the effectiveness of the developed system.
  • Thumbnail Image
    Conference Object
    Citation - WoS: 3
    Citation - Scopus: 3
    Locally-Weighted Template-Matching Based Prediction for Cloud-Based Image Compression
    (IEEE, 2016) Begaint, Jean; Thoreau, Dominique; Guillotel, Philippe; Turkan, Mehmet
    Thanks to the increasing number of images stored in the cloud, external image redundancies can be leveraged to efficiently compress images by exploiting inter-images correlations. In this paper, we propose a novel cloud-based image coding scheme. Unlike current state-of-the-art systems, our method relies on a data dimensionality reduction technique. A global compensation is associated to a locally-weighted template matching compensation method to predict a reference frame, to be then differential-coded with classic video coding tools. Experimental results demonstrate that the proposed approach yields significant rate-distortion performance improvements compared to current image coding solutions.
  • Thumbnail Image
    Conference Object
    Citation - WoS: 10
    Citation - Scopus: 47
    A Comparative Analysis on Fruit Freshness Classification
    (IEEE, 2019) Karakaya, Diclehan; Ulucan, Oguzhan; Turkan, Mehmet
    Automatic classification of food freshness plays a significant role in the food industry. Food spoilage detection from production to consumption stages needs to be performed minutely. Traditional methods which detect the spoilage of food are slow, laborious, subjective and time consuming. As a result, fast and accurate automatic methods need to be introduced to industrial applications. This study comparatively analyses an image dataset containing samples of three types of fruits to distinguish fresh samples from those of rotten. The proposed vision based framework utilizes histograms, gray level co-occurrence matrices, bag of features and convolutional neural networks for feature extraction. The classification process is carried out through well-known support vector machines based classifiers. After testing several experimental scenarios including binary and multi-class classification problems, it turns out to be the highest success rates are obtained consistently with the adoption of the convolutional neural networks based features.
  • Thumbnail Image
    Conference Object
    Smartphone Platform for Image-Based Cell Confluency Analysis
    (Institute of Electrical and Electronics Engineers Inc., 2025) Turkan, Mehmet; Cetin, Arif E.; Avci, Meryem Beyza