Food recognition using neural network classifier and multiple hypotheses image segmentation

ABSTRACT

This paper proposes the multiple-hypotheses image segmentation and feed-forward neural network classifier for food recognition to improve the performance. Initially, the food or meal image is given as input. Then, the segmentation is applied to identify the regions, where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the features of every food item are extracted by the global feature and local feature extraction. After the features are obtained, the classification is performed for each segmented region using a feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food volume and (ii) calorie and nutrition measure based on mass value. The experimental results and performance evaluation are validated. The outcome of the proposed method attains 0.947 for Macro Average Accuracy (MAA) and 0.959 for Standard Accuracy (SA), which provides better classification performance.     

A semantic modeling approach for image retrieval by content

We introduce a semantic data model to capture the hierarchical, spatial, temporal, and evolutionary semantics of images in pictorial databases. This model mimics the user's conceptual view of the image content, providing the framework and guidelines for preprocessing to extract image features. Based on the model constructs, a spatial evolutionary query language (SEQL), which provides direct image object manipulation capabilities, is presented. With semantic information captured in the model, spatial evolutionary queries are answered efficiently. Using an object-oriented platform, a prototype medical-image management system was implemented at UCLA to demonstrate the feasibility of the proposed approach.     

The Effect of the Charge Fluctuation of Dust Parti-cles on Ion-acoustic Wave Excited Through Ionization Instability

The effect of the charge fluctuation of dust particles on ion acoustic wave (IAW) excited through ionization instability was investigated. The hydrodynamic equations and linear time-dependent perturbation theory served as the starting point of theory, by which the dispersion relation and growth rate of the IAW were given. By comparing the results with the case of constant dust charges, it was found that the charge fluctuation of dust particles reduces the instability of the wave mode.     

A Multiagent System for the Reliable Execution of Automatically Composed Ad-hoc Processes

This article presents an architecture to automatically create ad-hoc processes for complex value-added services and to execute them in a reliable way. The uniqueness of ad-hoc processes is to support users not only in standardized situations like traditional workflows do, but also in unique non-recurring situations. Based on user requirements, a service composition engine generates such ad-hoc processes, which integrate individual services in order to provide the desired functionality. Our infrastructure executes ad-hoc processes by transactional agents in a peer-to-peer style. The process execution is thereby performed under transactional guarantees. Moreover, the service composition engine is used to re-plan in the case of execution failures. The work presented in this article was supported by the Swiss National Science Foundation as part of the project MAGIC (FNRS-68155), as well as by the Swiss National Funding Agency OFES as part of the European projects KnowledgeWeb (FP6-507482) and DIP (FP6-507483). Authors in alphabetic order     

Thermogravimetric Determination of Carbon, Nitrogen, and Oxygen in Aluminum Nitride

A thermogravimetric method for the measurement of carbon, nitrogen, and oxygen in aluminum nitride is described. Since carbon oxidation occurs at lower temperatures than the oxidation of the aluminum compounds, thermogravimetric analyses in the respective temperature regimes can yield measurement of the oxygen, nitrogen, and carbon content. Thermogravimetric analyses were performed on mixtures of aluminum nitride and carbon with various concentrations in order to evaluate the accuracy of this method. The results were compared with those obtained by the hot gas extraction method. Errors produced by overlapping of the temperature ranges of the reactions were evaluated and experimental conditions were optimized to minimize error. This method can produce reliable results at elemental concentrations higher than a few percent. The absolute errors of the C/AI, N/Al, and O/Al atomic ratios were less then 0.02. The detection limit was evaluated to 0.2 wt% of each element. The applicability of the method to the study of the kinetics of the nitridation reaction was demonstrated.     

Research on the Distant Hybrids of Wheat Obtained via Low-Energy Ion-Beam Implantation

Abstract The whole DNA of soybean was implanted into four varieties of wheat of Zhongyu5, Huaiyin 9628, Wenyou 1, Jimai 5 respectively via ion-beam mediation. There were 5 plantsobtained whose protein content was higher than 18.5%, the highest one was 21.44%. There were 3plants obtained whose protein content was lower than 11.5%, the lowest one was 10.96%. We cansee that the whole DNA of soybean transformed into wheat via ion beam implantation can inducethe increase in wheat protein content dramatically. The result also shows that the transformationefficiency of different gene types of wheat receptor varies greatly that the implanting time has acertain effect on the efficiency of transformation.     

Intestinal pseudo-obstruction associated with oral morphine

Infusion of the GPIIb/IIIa-inhibitor MK383 inhibits thrombin generation in platelet rich plasma by interfering with the production of platelet procoagulant phospholipid exposure. The effect is similar to that of 0.2 U/ml of heparin. Heparin infusion, well known to inhibit thrombin generation by fostering antithrombin activity, inhibits the formation of platelet-derived procoagulant microparticles, probably by decreasing the formation of free thrombin, which, under our circumstances, is the main platelet activator.     

Poisson Shot Noise Removal by an Oracular Non-Local Algorithm

Journal of Mathematical Imaging and Vision - In this paper, we address the problem of denoising images obtained under low-light conditions for the Poisson shot noise model. Under such conditions,...     

Face recognition with lattice independent component analysis and extreme learning machines

We focus on two aspects of the face recognition, feature extraction and classification. We propose a two component system, introducing Lattice Independent Component Analysis (LICA) for feature extraction and Extreme Learning Machines (ELM) for classification. In previous works we have proposed LICA for a variety of image processing tasks. The first step of LICA is to identify strong lattice independent components from the data. In the second step, the set of strong lattice independent vector are used for linear unmixing of the data, obtaining a vector of abundance coefficients. The resulting abundance values are used as features for classification, specifically for face recognition. Extreme Learning Machines are accurate and fast-learning innovative classification methods based on the random generation of the input-to-hidden-units weights followed by the resolution of the linear equations to obtain the hidden-to-output weights. The LICA-ELM system has been tested against state-of-the-art feature extraction methods and classifiers, outperforming them when performing cross-validation on four large unbalanced face databases.