Mehmet Kemal Güllü

Modified phase-correlation based robust hard-cut detection with application to archive film

This paper targets hard-cut detection for archive film, i.e., mainly black-and-white videos from the beginning of the last century, which is a particularly difficult task due to heavy visual degradations encountered in the sequences. A robust hard-cut detection system based on modified phase correlation is presented. Phase-correlation-based hard-cut detection is carried out using spatially sub-sampled video frames, and a candidate hard-cut is indicated in the case of low correlation. A double thresholding approach consisting of a global threshold used in conjunction with an adaptive local threshold is used to detect candidate hard-cuts. For uniformly colored video frames the phase correlation is extremely sensitive to noise and visual defects. Mean and variance based simple heuristic false removal at uniformly colored video frames is used at the final stage to prevent false detections in such cases. The paper provides a through theoretical analysis to show the usefulness of spatial sub-sampling. Furthermore through experimental results are presented for visual defects encountered in archive film material, to present the effectiveness of the proposed approach.

Membership function adaptive fuzzy filter for image sequence stabilization

In this paper a novel adaptive fuzzy: image sequence stabilization system is proposed for the motion correction part of digital image stabilizers. The proposed stabilizer is based on smoothing of absolute frame positions. Initially a short mean filter is applied to raw absolute frame displacements as pre-process, to reduce the dynamic range of the fuzzy system input. This enables the fuzzy system to give appropriate responses with a fewer number of membership functions, hence provides improved performance at reduced computational load. Fuzzy stabilization is then achieved through fuzzy correction mapping. Output membership functions of the fuzzy system are continuously adapted so as to constitute a membership function adaptive fuzzy filtering process. The proposed membership function adaptive fuzzy filter based image sequence stabilization system is shown to provide excellent stabilization as well as intentional camera movement presentation performance, superior to previously reported systems.

Hyperspectral Image Classification Using Empirical Mode Decomposition With Spectral Gradient Enhancement

This paper proposes to use empirical mode decomposition (EMD) with spectral gradient enhancement to increase the classification accuracy of hyperspectral images with support vector machine (SVM) classification. Recently, it has been shown that higher hyperspectral image classification accuracy can be achieved by using 2-D EMD that is applied to each hyperspectral band separately to obtain the intrinsic mode functions (IMFs) of each band, while the sum of the IMFs are used as feature data in the SVM classification process. In the previous approach, IMFs have been summed directly, i.e., with equal weights. It is shown in this paper, that it is possible to significantly increase the classification accuracy by using appropriate weights for the IMFs in the summation process. In the proposed approach, the weights of the IMFs are obtained so as to optimize the total absolute spectral gradient, and a genetic algorithm-based optimization strategy has been adopted to obtain the weights automatically in this way. While the 2-D EMD basically provides spatial processing, the proposed method further incorporates spectral enhancement into the process. It is shown that a significant increase in hyperspectral image classification accuracy can be achieved using the proposed approach.

Spatial Resolution Enhancement of Hyperspectral Images Using Unmixing and Binary Particle Swarm Optimization

Hyperspectral imaging provides high spectral resolution and thereby improved classification, detection, and recognition capabilities with respect to standard imaging systems. However, hyperspectral images generally have low spatial resolution, varying from a few to tens of meters, resulting from technical limitations such as platform data storing capacity and satellite-to-ground transmission bandwidth. Spectral unmixing provides information on pixels in terms of abundances of pure spectral signatures, without providing spatial distribution at subpixel level. Multisensor image fusion approaches can provide such information but require an additional image with higher spatial resolution that is acquired in similar conditions with the hyperspectral image. In this letter, a novel spatial resolution enhancement method using fully constrained least squares (FCLS) spectral unmixing and spatial regularization based on modified binary particle swarm optimization is proposed to achieve spatial resolution enhancement in hyperspectral images, without using an additional image with higher spatial resolution. The proposed method has a highly parallel nature with respect to its counterparts in the literature and is fit to be adapted to field-programmable gate array architecture.

Weighted constrained one-bit transform based fast block motion estimation

Block based motion estimation (ME) techniques based on low bit-depth representation have been proposed in the literature to reduce the computational complexity of ME. One-bit transform based ME methods are pioneers in this field. These methods derive one-bit images using an adaptive thresholding scheme, and perform block based ME on one-bit images using simplified matching criteria. Recently, constrained one-bit transform (C-1BT) based ME has been proposed to increase ME performance of 1BT based ME, restraining pixels with values close to the adaptive threshold throughout the matching. In this work, a weighted constraint strategy is proposed to increase the matching performance of C-1BT based ME. Instead of the one-bit constraint mask used in the literature, a two-bit constraint is computed according to the difference between a pixel and its 1BT threshold value, novel to this paper. Experimental results show that the proposed method improves the ME performance of C-1BT, and outperforms other low bit-depth based ME methods at macro-block level.

Image processing-aided working posture analysis

OWAS method is adapted to an integrated software as a prototype.It operates completely computer-aided with the help of image processing techniques.That models performance is high while robust recording conditions can be settled.Necessity of expert analyst is eliminated.The model will support the common use of OWAS in industry. Musculoskeletal Disorders (MSDs) rank among the commonest health problems both in the frequency of concurrency and in the money spent on these disorders, which mainly stem from poor working posture it also negatively affects employees in terms of job productivity, life quality, and both physical and social activities. Analyzing and improving working postures with scientific methods provides significant contributions in the field of controlling job performance and decreasing MSDs. OWAS (Ovako Working Posture Analyzing System) is one of the methods for analyzing working postures and can be applied to very diverse areas successfully. In this study, a prototype of integrated software, which is based on image processing techniques, was developed (I-OWAS), and the performance of the model was presented. I-OWAS begins with separating the video film into frames, producing OWAS codes belonging to working posture in each frame, and then classifying the images according to risk categories. Despite OWAS being a successful method for analyzing working postures, it requires an expert analysis. Also the manual analyzing process is so laborious and time consuming. I-OWAS provide the computer support for the manual coding stage and eliminates the need for an expert analyst; hence, the method can be widely used in industry.

Endmember Extraction Guided by Anomalies and Homogeneous Regions for Hyperspectral Images

Endmember extraction is the process of selecting pure spectral signatures of materials from hyperspectral data. Most of the endmember extraction methods in the literature use only the spectral information, and disregard the spatial composition of the image. Spatial-spectral preprocessing methods, motivated by the assumption that endmembers are more likely to be located in homogenous regions, can increase the performance of endmember extraction by directing the extraction process to homogenous regions. However, such an approach generally results in a failure of extracting anomalous or scarce endmembers, which can be important in practical applications, e.g., to extract endmembers of materials such as landmines, rare minerals, or stressed crops. Although anomaly detection can be applied in parallel to endmember extraction, the process of endmember extraction and unmixing provides a summary of the data, which is important for concepts such as data scanning and compression, and disregarding anomalous endmembers in such a summary or compression of big data may result in undesired consequences for many application fields. In this paper, an approach that guides the endmember extraction process to spatially homogenous regions instead of transition areas, while also extracting anomalous pixel vectors as endmembers, is proposed. The proposed approach can be used with any spectral-based endmember extraction method. The experimental results validate the approach for both synthetic and real hyperspectral images.

Integrating anomaly detection to spatial preprocessing for endmember extraction of hyperspectral images

Spectral unmixing is the process of identifying pure spectral signatures, called endmembers, from a hyperspectral data, and then expressing each pixel vector in terms of the fractional abundances of these endmembers. Most of the endmember extraction methods in the literature use only the spectral information, whereas the spatial composition of the data is disregarded. Spatial preprocessing methods, that are motivated by the assumption that endmembers are more likely to be located in homogeneous regions instead of transition areas, can alleviate this drawback and hence increase the performance. However, such a preprocessing approach generally results in a failure of extracting anomalous endmembers which can be of importance for many applications. In this paper, a preprocessing approach that guides the endmember extraction process to homogenous regions while retaining the anomaly points, by combining spatial preprocessing with anomaly detection, is proposed.

Plastic waste sorting using infrared hyperspectral imaging system

The inherent chemical properties of materials can be brought into perspective using the large amount of spectral information provided by hyperspectral imaging systems. Therefore, the utilization of hyperspectral imaging in industrial applications is gradually increasing. One of the industrial sectors that can benefit from the advantages of hyperspectral imaging is recycling. Plastics which have different chemical properties (PP, PE, PVC, PET and PS) need sorting for plastic waste recycling. In this study, different types of plastics in hyperspectral images acquired using a shortwave infrared (SWIR) hyperspectral imaging system are successfully sorted.

Enhancement of fog degraded images using empirical mode decomposition

Images can have poor visibility, contrast and colors in foggy weather conditions. Therefore it is required to enhance visual quality of the fog-degraded images. In this paper we present a new method based on an Empirical Mode Decomposition (EMD) for fog-degraded image enhancement. Initially each spectral component of the fog-degraded image is decomposed into Intrinsic Mode Functions (IMFs) using EMD. Then the enhanced image is constructed by combining the IMFs of spectral channels with optimum weights in order to obtain an enhanced image with increased visual quality. The optimal weight estimation process is carried out automatically using genetic algorithm. Eventually, image enhancement is completed performing color correction followed by a de-quantization.