A review of wave-net identical learning &; filling-in in a decomposition space of (JPG-JPEG) sampled images

Continuous flow to send images via encrypted wireless channels may reduce the efficiency of transmission. This is due to the damage or loss of the numerous macro-blocks from these images. Therefore, it is difficult to rebuild these patches from the point of reception. Many algorithms have been proposed in the past decade, particularly error concealment (EC) algorithms. In this paper, we focus on the algorithms that have high efficiency to fill-in the corrupted patches. On the other hand, we also present a new way of detecting the horizontal and vertical gradients especially, in the un-smooth patches. This improves the edge detector filter. Ultimately, a novel scheme for vertical and horizontal interpolation between the corrupted pixels and the non-corrupted adjacent pixels is achieved by improving the efficiency of filling-in. We used a new technique known as the wave-net model. This model combines the wavelet with the neural network classifier (NNC). The neural network was trained in advance to reduce the error extent for the pixels that may occur in the error. The experimental results were convincing and close to the desired. The proposed method is able to enhance image quality in term of both visual perception and the blurriness effects (BE).     

Oil palm bunch ripeness classification using fluorescence technique

Oil palm is Malaysia’s major agriculture product and it covers approximately 5 million hectares of Malaysia’s land. Limited land resources have been an important factor that motivated the need to increase oil extraction rate (OER). OER of oil palm fresh fruit bunches (FFB) depends highly on their maturity stage. The ripe oil palm FFB will produce high OER while the under ripe and over ripe oil palm FFB will produce less oil. Thus, this paper presents a method of classification between oil palm FFB into ripe, under-ripe and over-ripe categories. This research was done at an oil palm plantation in peninsular Malaysia. A total of two-hundred and ten oil palm FFB that consist of seventy bunches for each category of under-ripe, ripe and over-ripe had been used. Each bunch was scanned ten times randomly with a hand-held multi-parameter fluorescence sensor called Multiplex®3. The parameter measured was the Blue-to-Red Fluorescence Ratio (BRR_FRF) obtained from blue-green (447 nm) and far-red (685 nm) emission signal by using ultraviolet (UV) light emitting diode as excitation light source. The novel contribution of this research is to prove that the oil palm FFB maturity can be determined using the Blue-to-Red Fluorescence ratio index. This is based to our finding of a significant difference among the three categories of ripeness based on the parameter. Classification and Regression Tree (C&RT) method was proposed in this paper. Hundred-fifty samples were used to develop the model by trained it using C&RT method and the remaining sixty samples for the test component. By using the C&RT method, the results show the best accuracy of overall testing classification is 90%. This research will be useful for future development of non-destructive, automatic and real time oil palm FFB grading system.     

Biohydrogen production from sugarcane bagasse hydrolysate by elephant dung: Effects of initial pH and substrate concentration

Pre-heated elephant dung was used as inoculum to produce hydrogen from sugarcane bagasse (SCB) hydrolysate. SCB was hydrolyzed by H₂SO₄ or NaOH at various concentrations (0.25-5% volume) and reaction time of 60 min at 121 °C, 1.5 kg/cm² in the autoclave. The optimal condition for the pretreatment was obtained when SCB was hydrolyzed by H₂SO₄ at 1% volume which yielded 11.28 g/L of total sugar (1.46 g glucose/L; 9.10 g xylose/L; 0.72 g arabinose/L). The maximum hydrogen yield of 0.84 mol H₂/mol total sugar and the hydrogen production rate of 109.55 mL H₂/L day were obtained at the initial pH 6.5 and initial total sugar concentration 10 g/L. Hydrogen-producing bacterium (Clostridium pasteurianum) and non hydrogen-producing bacterium (Flavobacterium sp.) were dominating species in the elephant dung and in hydrogen fermentation broth. Sporolactobacillus sp. was found to be responsible for a low hydrogen yield obtained.     

Simultaneous saccharification and fermentation of cellulose for bio-hydrogen production by anaerobic mixed cultures in elephant dung

The objective of this study was to optimize the culture conditions for simultaneous saccharification and fermentation (SSF) of cellulose for bio-hydrogen production by anaerobic mixed cultures in elephant dung under thermophilic temperature. Carboxymethyl cellulose (CMC) was used as the model substrate. The investigated parameters included initial pH, temperature and substrate concentration. The experimental results showed that maximum hydrogen yield (HY) and hydrogen production rate (HPR) of 7.22 ± 0.62 mmol H₂/g CMC_added and 73.4 ± 3.8 mL H₂/L h, respectively, were achieved at an initial pH of 7.0, temperature of 55 °C and CMC concentration of 0.25 g/L. The optimum conditions were then used to produce hydrogen from the cellulose fraction of sugarcane bagasse (SCB) at a concentration of 0.40 g/L (equivalent to 0.25 g/L cellulose) in which an HY of 7.10 ± 3.22 mmol H₂/g cellulose_added. The pre-dominant hydrogen producers analyzed by polymerase chain reaction-denaturing gel gradient electrophoresis (PCR-DGGE) were Thermoanaerobacterium thermosaccharolyticum and Clostridium sp. The lower HY obtained when the cellulose fraction of SCB was used as the substrate might be due to the presence of lignin in the SCB as well as the presence of Lactobacillus parabuchneri and Lactobacillus rhamnosus in the hydrogen fermentation broth.     

Volatile compounds in Bacillus‐fermented soybeans

Thua nao, a traditional, proteolytic, fermented soybean condiment of northern Thailand, was prepared from cooked whole soybeans by natural flora fermentation. The microbial flora during the fermentation was dominated by Bacillus species. The formation of volatile compounds during the fermentation was studied. In addition, the volatile compounds of two samples of commercial dried thua nao and two samples of commercial Japanese natto were analysed. Fermentation led to a large increase in the concentration of total volatile compounds, from 35 µg kg^?1 wet weight in cooked soybeans to 3500 µg kg^?1 wet weight in 72 h fermented material. The major volatile compounds in fermented beans were 3‐hydroxybutanone (acetoin), 2‐methlybutanoic acid, pyrazines, dimethyl disulphide and 2‐pentylfuran. Sun drying of 72 h fermented material resulted in the loss of 65% of total volatiles, including important aroma compounds. The commercial dried thua nao samples had low concentrations of total volatile compounds (380 µg kg^?1 wet weight). It is suggested that improved drying/preservation methods are needed to retain aroma compounds in the traditional products. The natto samples were devoid of aldehydes, aliphatic acids and esters, and sulphur compounds, whereas the thua nao samples contained a diversity of these compounds. Previous investigators have reported these compounds in natto and it is not possible to suggest the existence of systematic differences between the volatile compounds in traditional thua nao prepared with an undefined, mixed microbial flora and those in natto fermented with Bacillus subtilis. © 2001 Society of Chemical Industry     

Cross‐sectional area calculation for arbitrary shape in the image using star algorithm with Green's theorem

Calculation of the cross‐sectional area is an important diagnostic tool in medical imaging modality. Curvature points arrangement (CPA) is an important step in the calculation, where the Star algorithm had been shown to be effective in segmenting the carotid artery. The algorithm however works under the assumption of circular or ellipsoid shapes, and the ability to determine its center of gravity is done by exploiting the features of equi‐space diameter of the circle. In this paper, a method of calculation of the cross‐sectional area of an arbitrary shape is discussed. The Star algorithm is modified to arrange the points of the object's edge through the CPA process in order to form a simple closed curve. Several rays are emanated from a point inside the region of interest with different angles to the far points within the segmented area. The cross‐sectional area is then calculated by using Green's theorem. To validate the concepts, several regular shaped images with different noise types (Gaussian, speckles, and salt and pepper) and ultrasound images are used in the experiments. The result shows that this method can calculate the cross‐sectional area with negligible error for an arbitrary object within the image and with different types of noises. © 2013 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

Review of brain MRI image segmentation methods

Brain image segmentation is one of the most important parts of clinical diagnostic tools. Brain images mostly contain noise, inhomogeneity and sometimes deviation. Therefore, accurate segmentation of brain images is a very difficult task. However, the process of accurate segmentation of these images is very important and crucial for a correct diagnosis by clinical tools. We presented a review of the methods used in brain segmentation. The review covers imaging modalities, magnetic resonance imaging and methods for noise reduction, inhomogeneity correction and segmentation. We conclude with a discussion on the trend of future research in brain segmentation.     

Semi-automatic detection and counting of oil palm trees from high spatial resolution airborne imagery

Plantation inventory and management require a range of fine-scale remote-sensing data. Remote-sensing images with high spatial and spectral resolution are an efficient source of such information. This article presents an approach to the extraction and counting of oil palm trees from high spatial resolution airborne imagery data. Counting oil palm trees is a crucial problem in specific agricultural areas, especially in Malaysia. The proposed scheme comprises six major parts: (1) discrimination of oil palms from non-oil palms using spectral analysis, (2) texture analysis, (3) edge enhancement, (4) segmentation process, (5) morphological analysis and (6) blob analysis. The average accuracy obtained was 95%, which indicates that high spatial resolution airborne imagery data with an appropriate assessment technique have the potential to provide us with vital information for oil palm plantation management. Information on the number of oil palm trees is crucial to the ability of plantation management to assess the value of the plantation and to monitor its production.     

Review of liver segmentation and computer assisted detection/diagnosis methods in computed tomography

Computed tomography (CT) imaging remains the most utilized modality for liver-related cancer screening and treatment monitoring purposes. Liver, liver tumor and liver vasculature segmentation from CT data is a prerequisite for treatment planning and computer assisted detection/diagnosis systems. In this paper, we present a survey on liver, liver tumor and liver vasculature segmentation methods that are using CT images, recent methods presented in the literature are viewed and discussed along with positives, negatives and statistical performance of these methods. Liver computer assisted detection/diagnosis systems will also be discussed along with their limitations and possible ways of improvement. In this paper, we concluded that although there is still room for improvement, automatic liver segmentation methods have become comparable to human segmentation. However, the performance of liver tumor segmentation methods can be considered lower than expected in both automatic and semi-automatic methods. Furthermore, it can be seen that most computer assisted detection/diagnosis systems require manual segmentation of liver and liver tumors, limiting clinical applicability of these systems. Liver, liver tumor and liver vasculature segmentation is still an open problem since various weaknesses and drawbacks of these methods can still be addressed and improved especially in tumor and vasculature segmentation along with computer assisted detection/diagnosis systems.     

Adaptive‐search template matching technique based on vehicle acceleration for monocular visual odometry system

One of the important tasks of an autonomous mobile vehicle is the reliable and fast estimation of its position over time. This paper presents the development of an adaptive technique to hasten and improve the quality of correlation‐based template matching for monocular visual odometry systems that estimate the relative motion of ground vehicles in low‐textured environments. Moreover, the factors that can affect the maximum permissible vehicle driving speed were determined and the related equations were derived. The developed system uses a single downward‐facing monocular camera installed at an optimum location to avoid the negative effect of directional sunlight and shadows which can disturb the correlation. In addition, the normalized cross‐correlation method is implemented to calculate the pixel displacement between image frames. Although this method is highly effective for template matching because of its invariance to linear brightness and contrast variations, it incurs high computational cost. Thus, the optimal sizes of image template and matching search area are selected and their locations are dynamically changed according to vehicle acceleration, in order to achieve a compromise between the performance and the computational cost of correlation. The proposed technique increases the allowable vehicle driving speed and reduces the probability of template false‐matching. Moreover, compared to traditional full search matching techniques, the adaptive technique demonstrates high efficiency and accuracy and improves the quality and speed of the correlation with more than 87% of reduction in computational cost. © 2016 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.