Ozkan, Savas
Ozkan, Akin
In this paper, we propose a kinship generator network that can synthesize a possible child face by analyzing his/her parent's photo. For this purpose, we focus on to handle the scarcity of kinship datasets throughout the paper by proposing novel solutions in particular. To extract robust features, we integrate a pre-trained face model to the kinship face generator. Moreover, the generator network is regularized with an additional face dataset and adversarial loss to decrease the overfitting of the limited samples. Lastly, we adapt cycle-domain transformation to attain a more stable results. Experiments are conducted on Families in the Wild (FIW) dataset. The experimental results show that the contributions presented in the paper provide important performance improvements compared to the baseline architecture and our proposed method yields promising perceptual results.
25th IEEE International Conference on Image Processing (ICIP)


Image generation by back-propagation on input using a discriminator network
Taplı, Merve; Akbaş, Emre; Department of Computer Engineering (2021-9-08)
In this thesis, we propose an image generation method that only involves a discriminator network; no generator or decoder networks are required. To generate an image, we iteratively apply an adversarial attack on the discriminator by updating the input image, which is noise at the beginning, to maximize the discriminator's output score. Generated images are then used as negative examples, together with the real images as positive examples, to fine-tune the discriminator. After several rounds of generation a...
Image generation using only a discriminator network with gradient norm penalty
Yeşilçimen, Cansu Cemre; Akbaş, Emre; Department of Computer Engineering (2022-9)
This thesis explores the idea of generating images using only a discriminator network by extending a previously proposed method (Tapli, 2021) in several ways. The base method works by iteratively updating the input image, which is pure noise at the beginning while increasing the discriminator's score. We extend the training procedure of the base network by adding the following new losses: (i) total variation, (ii) N-way classification (if labels are available), and (iii) gradient norm penalty on real exam...
GANILLA: Generative adversarial networks for image to illustration translation
Hicsonmez, Samet; Samet, Nermin; Akbaş, Emre; DUYGULU ŞAHİN, PINAR (Elsevier BV, 2020-03-01)
In this paper, we explore illustrations in children's books as a new domain in unpaired image-to-image translation. We show that although the current state-of-the-art image-to-image translation models successfully transfer either the style or the content, they fail to transfer both at the sametime. We propose a new generator network to address this issue and show that the resulting network strikes a better balance between style and content. There are no well-defined or agreed-upon evaluation metrics for unp...
Position estimation for timing belt drives of precision machinery using structured neural networks
KILIÇ, Ergin; DOĞRUER, CAN ULAŞ; Dölen, Melik; Koku, Ahmet Buğra (2012-05-01)
This paper focuses on a viable position estimation scheme for timing-belt drives using artificial neural networks. In this study, the position of a carriage (load) is calculated via a structured neural network topology accepting input from a position sensor on the actuator side of the timing belt. The paper presents a detailed discussion on the source of transmission errors. The characteristics of the error in different operation regimes are exploited to construct different network topologies. That is, a re...
Smart toys for preschool children: A design and development research
KARA, NURİ; Çağıltay, Kürşat (Elsevier BV, 2020-01-01)
The purpose of this study is to devise guidelines for designing, developing, and using a smart toy for preschool children. Smart toys are technologically developed toys constructed with a meaningful purpose. This study uses the design and development research method. In the analysis phase, the smart toy developed in the pilot study was analyzed. In the design phase, focus group meetings were held with early childhood teachers to determine the objectives, story, and storyboard of the smart toy. In the develo...
Citation Formats
S. Ozkan and A. Ozkan, “KINSHIPGAN: SYNTHESIZING OF KINSHIP FACES FROM FAMILY PHOTOS BY REGULARIZING A DEEP FACE NETWORK,” Athens, GREECE, 2018, p. 2142, Accessed: 00, 2020. [Online]. Available: