Maryam Khanian - Academia.edu (original) (raw)

Papers by Maryam Khanian

Journal of Medical Signals & Sensors, 2014

Improving the quality of medical images at pre- and post-surgery operations are necessary for beg... more Improving the quality of medical images at pre- and post-surgery operations are necessary for beginning and speeding up the recovery process. Partial differential equations-based models have become a powerful and well-known tool in different areas of image processing such as denoising, multiscale image analysis, edge detection and other fields of image processing and computer vision. In this paper, an algorithm for medical image denoising using anisotropic diffusion filter with a convenient stopping criterion is presented. In this regard, the current paper introduces two strategies: utilizing the efficient explicit method due to its advantages with presenting impressive software technique to effectively solve the anisotropic diffusion filter which is mathematically unstable, proposing an automatic stopping criterion, that takes into consideration just input image, as opposed to other stopping criteria, besides the quality of denoised image, easiness and time. Various medical images ...

Motivated by the growing demand for interactive environments, we propose an accurate real-time 3D... more Motivated by the growing demand for interactive environments, we propose an accurate real-time 3D shape reconstruction technique. To provide a reliable 3D reconstruction which is still a challenging task when dealing with real-world applications, we integrate several components including (i) Photometric Stereo (PS), (ii) perspective Cook-Torrance reflectance model that enables PS to deal with a broad range of possible real-world object reflections, (iii) realistic lightening situation, (iv) a Recurrent Optimization Network (RON) and finally (v) heuristic Dijkstra Gaussian Mean Curvature (DGMC) initialization approach. We demonstrate the potential benefits of our hybrid model by providing 3D shape with highly-detailed information from micro-prints for the first time. All real-world images are taken by a mobile phone camera under a simple setup as a consumer-level equipment. In addition, complementary synthetic experiments confirm the beneficial properties of our novel method and its ...

Image restoration has been an active research area. Di erent formulations are e ective in high qu... more Image restoration has been an active research area. Di erent formulations are e ective in high qualityrecovery. Partial Di erential Equations (PDEs) have become an important tool in image processingand analysis. One of the earliest models based on PDEs is Perona-Malik model that is a kindof anisotropic di usion (ANDI) lter. Anisotropic di usion lter has become a valuable tool indi erent elds of image processing specially denoising. This lter can remove noises without degradingsharp details such as lines and edges. It is running by an iterative numerical method. Therefore, afundamental feature of anisotropic di usion procedure is the necessity to decide when to stop theiterations. This paper proposes the modi ed stopping criterion that from the viewpoints of complexityand speed is examined. Experiments show that it has acceptable speed without su ering from theproblem of computational complexity.

2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)

With recent innovations in dense image captioning, it is now possible to describe every object of... more With recent innovations in dense image captioning, it is now possible to describe every object of the scene with a caption while objects are determined by bounding boxes. However, interpretation of such an output is not trivial due to the existence of many overlapping bounding boxes. Furthermore, in current captioning frameworks, the user is not able to involve personal preferences to exclude out of interest areas. In this paper, we propose a novel hybrid deep learning architecture for interactive region segmentation and captioning where the user is able to specify an arbitrary region of the image that should be processed. To this end, a dedicated Fully Convolutional Network (FCN) named Lyncean FCN (LFCN) is trained using our special training data to isolate the User Intention Region (UIR) as the output of an efficient segmentation. In parallel, a dense image captioning model is utilized to provide a wide variety of captions for that region. Then, the UIR will be explained with the caption of the best match bounding box. To the best of our knowledge, this is the first work that provides such a comprehensive output. Our experiments show the superiority of the proposed approach over state-of-the-art interactive segmentation methods on several well-known datasets. In addition, replacement of the bounding boxes with the result of the interactive segmentation leads to a better understanding of the dense image captioning output as well as accuracy enhancement for the object detection in terms of Intersection over Union (IoU).

2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), Dec 1, 2017

Computational Visual Media

Photometric stereo is a fundamental technique in computer vision known to produce 3D shape with h... more Photometric stereo is a fundamental technique in computer vision known to produce 3D shape with high accuracy. It uses several input images of a static scene taken from one and the same camera position but under varying illumination. The vast majority of studies in this 3D reconstruction method assume orthographic projection for the camera model. In addition, they mainly use the Lambertian reflectance model as the way that light scatters at surfaces. Thus, providing reliable photometric stereo results from real world objects still remains a challenging task. We address 3D reconstruction by use of a more realistic set of assumptions, combining for the first time the complete Blinn-Phong reflectance model and perspective projection. Furthermore, we compare two different methods of incorporating the perspective projection into our model. Experiments are performed on both synthetic and real world images; the latter do not benefit from laboratory conditions. The results show the high potential of our method even for complex real world applications such as medical endoscopy images which may include many specular highlights.

In this paper, an application of reproducing kernel Hilbert space (RKHS) method is applied to sol... more In this paper, an application of reproducing kernel Hilbert space (RKHS) method is applied to solve system of Fredholm integro-differential equations. The exact solutions are represented in the form of series in the reproducing kernel space. Moreover, the approximate solutions u n (x), v n (x) are proved to converge to the exact solutions u(x), v(x), respectively. The results reveal that the RKHS is simple and effective.

Stereo (PS): Classic computer vision problem (Woodham, 1980) • Given: Multiple input images (≥ 3)... more Stereo (PS): Classic computer vision problem (Woodham, 1980) • Given: Multiple input images (≥ 3) of a static scene One and the same camera position Different illumination directions • Output: Surface normal vectors of photographed object • 3-D depth reconstruction by integration of surface normal vectors • Classic assumptions Orthographic projection performed by the camera Lambertian light reflectance Light Reflectance Model Blinn-Phong light reflectance model I = k d D M l d diffuse reflectance + ks S M α ls specular highlights I = I(x, y) is one grey-valued input image k d , ks material parameters for diffuse and specular light reflectance l d , ls light intensity parameter α roughness parameter l = l(x, y) light vector with components l 1 , l 2 , l 3 h = h(x, y) half-way vector between light vector and viewing direction of camera where        D = f∇u · (l 1 , l 2) − l 3 (x · ∇u + 1) M = f 2 2 + (x · ∇u + 1) 2 S = f∇u −∇u · x − 1 · l f 2 + 2 − x f f focal length of the cam...

Image restoration has been an active research area. Different formulations are effective in high ... more Image restoration has been an active research area. Different formulations are effective in high quality recovery. Partial Differential Equations (PDEs) have become an important tool in image processing and analysis. One of the earliest models based on PDEs is Perona-Malik model that is a kind of anisotropic diffusion (ANDI) filter. Anisotropic diffusion filter has become a valuable tool in different fields of image processing specially denoising. This filter can remove noises without degrading sharp details such as lines and edges. It is running by an iterative numerical method. Therefore, a fundamental feature of anisotropic diffusion procedure is the necessity to decide when to stop the iterations. This paper proposes the modified stopping criterion that from the viewpoints of complexity and speed is examined. Experiments show that it has acceptable speed without suffering from the problem of computational complexity.

Twelfth International Conference on Quality Control by Artificial Vision 2015, 2015

ABSTRACT Photometric stereo is a technique for estimating the 3-D depth of a surface using multip... more ABSTRACT Photometric stereo is a technique for estimating the 3-D depth of a surface using multiple images taken under different illuminations from the same viewing angle. Most existing models make use of Lambertian reflection and an orthographic camera as underlying assumptions. However, real-world materials often exhibit non-Lambertian effects such as specular highlights and for many applications it is of interest to consider objects close to the camera. In our work, we aim at addressing these issues. Together with perspective camera we employ a non-Lambertian reflectance model, namely the Blinn-Phong model which is capable to deal with specular reflection. Focussing on the effects of specular highlights, we performed a detailed study of one dimensional test cases showing important aspects of our method.