Correct Identification Of Objects Research Articles

Cognitive Processes Underlying the Weapon Identification Task: A Comparison of Models Accounting for Both Response Frequencies and Response Times

The weapon identification task (WIT) is a sequential priming paradigm designed to assess effects of racial priming on visual discrimination between weapons (guns) and innocuous objects (tools). We compare four process models that differ in their assumptions on the nature and interplay of cognitive processes underlying prime-related weapon-bias effects in the WIT. All four models are variants of the process dissociation procedure, a widely used measurement model to disentangle effects of controlled and automatic processes. We formalized these models as response time-extended multinomial processing tree models and applied them to eight data sets. Overall, the default interventionist model (DIM) and the preemptive conflict-resolution model (PCRM) provided good model fit. Both assume fast automatic and slow controlled process routes. Additional comparisons favored the former model. In line with the DIM, we thus conclude that automatically evoked stereotype associations interfere with correct object identification from the outset of each WIT trial.

The Concept of Implementation of Multifrequency RFID System Industrial Involvement in Laboratory Conditions

People have been dealing with the correct identification of objects for a long time. In industry, we cannot avoid this area, whether it is to identify people, semi-finished products or final products. Therefore, this article deals with the design of a multifrequency RFID system for industry 4.0. The idea of the article is to implement one type of identification technology for tracking objects using the radio frequency spectrum at different wavelengths. We have based our design on the built industrial-assembly line in the SmartTechLab laboratory, where we have implemented LF, HF and UHF systems connected by an industrial PLC into a complex system. In this article, we gradually focus on the selection of RFID systems, their cooperation and the design of connection to one portable box. Using an RFID box, we can monitor different types of objects and verify RFID reading using a single reading device or by creating portal RFID gateways. The implemented system consists of four middleware and four independent antennas that can cooperate. For proper operation, there is necessary implement not only hardware but also necessary software. The system can identify RFID tags in the range of 1 cm to several meters. Also, the advantage of the design is that it identifies all types of tags (industry, label, ceramic, laundry, paper). One of the main benefits of the design is modularity, mobility and the creation of a robust design that can be used for measurements in companies and also for educating students in laboratory conditions. The whole system is designed to meet the requirements of Industry 4.0 and improve the competitiveness of businesses.

Classifying Disease in Fruit using Machine Learning

India is agricultural country and Indian farmer select wide selection of fruit and vegetable crops. The cultivation of crops can be improved by the technological support. Fruits and vegetables losses are caused by disease. Diseases are seen on the leaves and fruits of plant, therefore disease detection plays a crucial role in cultivation of crops. Pathogens, fungi, microorganism, bacteria and viruses are sorts of fruit diseases also unhealthy environment is responsible for diseases. There are many techniques to spot diseases in fruits in its early stages. Hence, there's a requirement of automatic fruit unwellness detection system within the early stage of the unwellness. The aim is to detect the fruit disease, this method take input as image of fruit and determine it as infected or non- infected. The proposed method is based on the use of Scale-invariant Feature Transform (SIFT) Model with the desirable goal of accurate and fast classification of fruits. The SIFT features are local and based on the appearance of the object at particular interest points, and are invariant to image scale and rotation. They are also robust to changes in illumination, noise, and minor changes in viewpoint on image processing theory. SIFT have significant advantages because of their high accuracy, relatively easy to extract and allow for correct object identification with low probability of mismatch. Besides, they do not need an outsized number of coaching samples to avoid overfitting.

Measuring the Effectiveness of a Radio-Identification System

Conducted measurements of qualitative informative features for object recognition determined the most effective methods for measuring them. For this purpose, it is proposed to use the method of digital spectral analysis “thermal noise”, which will provide a significant increase in resolution and measurement accuracy of object characteristics. Experimental studies have shown that to increase the likelihood of correct identification of objects by existing radio-technical identification systems, it is necessary to measure the highly informative characteristics of objects - their radar long-range portraits. Measurement of such portraits is proposed to carry out through the use of broadband and especially ultra-wideband signals, with high stability of the complex frequency characteristics of the receiving and transmitting paths of radar stations. In particular, the proposed structure of the construction of an experimental measuring complex and the principle of its operation for measuring radar distance portraits of identification objects.

Combining Zernike moment and complex wavelet transform for human object classification

Human object classification is an important problem for smart video surveillance, where we classify human object in real scenes. In this paper, we have proposed a method for human object classification, which classify the object present in a scene into one of the two classes: human and non-human. The proposed method uses combination of Daubechies complex wavelet transform and Zernike moment as a feature of object. The motivation behind using combination of these two as a features of object, because shift-invariance and better edge representation property makes Daubechies complex wavelet transform suitable for locating object, whereas rotation invariance property of Zernike moment is also helpful for correct object identification. We have used Adaboost as a classifier for classification of the objects. The proposed method has been tested on different standard dataset. Quantitative experimental evaluation result shows that the proposed method gives better performance than other state-of-the-art methods for human object classification.

Neuropsychological evidence for the temporal dynamics of category-specific naming

ABSTRACTMultiple accounts have been proposed to explain category-specific recognition impairments. Some suggest that category-specific deficits may be caused by a deficit in recurrent processing between the levels of a hierarchically organized visual object recognition system. Here, we tested predictions of interactive processing theories on the emergence of category-selective naming deficits in neurologically intact observers and in patient GA, a single case showing a category-specific impairment for natural objects after a herpes simplex encephalitis infection. Fragmented object outlines were repeatedly presented until correct naming occurred (maximum 10 times), and the fragments increased in length with every repetition. We studied how shape complexity, object category, and fragment curvature influence the timing of correct object identification. The results of a survival analysis are consistent with the idea that deficits in recurrent processing between low- and high-level visual object representations can cause category-selective impairments.

The relation of experience in osteopathic palpation and object identification

BackgroundTo determine whether osteopathic medical students, fellows, residents, and practicing physicians differ in their ability to identify inanimate objects and if these skills relate to palpatory experience.MethodsFifteen commonly known objects were fixed to a board and blinded with a cotton cloth. In Part I of testing, participants were asked to identify 9 objects, with choices provided. In Part II participants were asked to identify 6 objects using one word only. Part III consisted of identifying the shape of an object in Part II.ResultsEighty-nine osteopathic medical students, fellows, residents, and practicing physicians participated in the study. Overall, correct identification of objects was higher in Part I with choices than in Part II without choices available. No statistically significant difference was found among osteopathic medical students, fellows, residents, and practicing physicians in the correct identification of the objects.ConclusionsAccuracy in tactile identification of objects among varying levels of palpatory experience was not found. Correlation with clinical palpation cannot be made as it requires a subset of palpatory skills not tested in this study. Accuracy and measurement of palpation should be studied further to demonstrate if palpatory experience improves palpatory accuracy.

WE-E-134-06: Pilot Project to Test the Feasibility of Automating Quantitative Ultrasound Performance Testing

Purpose: A pilot project to test the feasibility of automating quantitative ultrasound performance testing in an effort to increase repeatability, accuracy, and efficiency. Methods: Images were acquired from the same phantom (Model ATS 570) with different transducers and base units. The phantom tests for image uniformity, near field ring down (1 mm to 9 mm), depth of penetration (up to 18 cm), vertical and horizontal distance accuracy (nominal distances of 30 to 40 mm), axial and lateral spatial resolution (down to 1 mm), and contrast resolution (+/− 6 dB and +/− 3dB). Images were loaded into MatLab software where algorithms were developed and used to identify phantom fiducials. Various spatial and frequency filters were applied to enhance image uniformity for processing. Performance of the MatLab analyzed images were assessed by verifying the correct identification of objects. Results: The program is semi autonomous in its ability to locate the image and adjust subsequent inspections with changing images. The software is capable of detecting the objects of interest. Examination of the MatLab analyzed images indicate the quantitative assessment of the ultrasound instruments can indeed be performed with comparable results to human evaluation. Location of fiducial edges and fiducial centroids can be reliably and repeatably identified to carry out the performance evaluation of the instrument. Intensities of contrast fiducials can be compared to background intensities for evaluation of system contrast. Conclusion: The positive results of the initial testing give reason to further develop the algorithms to more completely automate the ultrasound quantitative analysis. More work will be performed to automatically identify manufacturer and transducer type from a default naming scheme and auto‐populate report sheets to increase testing efficiency and measurement repeatability. Conceivably, this type of program can be used in remote areas where physicists are scare and remote testing is feasible.

Information theoretic and machine learning approaches to quantify non-linear visual feature interaction underlying visual object recognition

Understanding what object features the visual system relies upon, when engaged in visual object recognition, is a longstanding challenge in psychophysical studies of visual perception. Although successful approaches have been developed to address this issue (e.g., image classification methods [1]), they have a major limitation: they can estimate the relationship between input visual images and output behavioral responses only under the assumption of a linear observer model (e.g., an observer performing a weighted sum of the information carried by individual pixels within an image). For instance, one popular image classification approach (named the Bubbles method [2]) recovers the salient features used by an observer to identify an object, by presenting the target object partially occluded by opaque masks punctured by transparent windows, and then averaging the trials yielding to correct object identification. However, this method cannot tell whether multiple salient features in an object interact non-linearly (e.g., whether those features need to be simultaneously visible for the object to be correctly identified). Here we propose two approaches to overcome this limitation. As a preliminary step, we simulated observers with various recognition strategies. Each observer had to discriminate bubbles-masked input images of two different objects, by comparing them with either linear or non-linear object templates. One of the object templates contained two features, whose evidence in any given input image was computed as the dot-product between the image and the features themselves. Finally, the overall template evidence was computed either as: 1) the product of the two feature evidences (AND-like feature interaction); 2) the maximum of the feature evidences (OR-like feature interaction); or 3) the sum of the feature evidences (linear interaction). The simulated observers served as benchmarks to validate two different feature-interaction analysis approaches. The first approach consisted of measuring the mutual information between the product/max/sum of every pair of pixels in the object image and the simulated observers’ responses. This approach successfully recovered the simulated feature interaction strategy, which was shown to convey significantly higher information about the observer’s response, as compared to the two other alternative strategies (permutation test; p < 106). The second approach consisted in fitting a model to the AND-like, non-linear observer’s responses, which could predict responses to novel input images. As a model we chose a regularized logistic regression classifier, which was fed with both individual pixel values and the product of pixel pairs. The classifier successfully generalized to unseen input images (training performance=100%, test performance=87%) and its maximal weights matched/captured the simulated feature interaction (e.g., pixels’ products had maximal weights). Finally, we also started applying sparse classifiers[3], which, by relying on diluted discrete weights, could potentially yield a cleaner (i.e., more parsimonious) estimate of salient object features and their interaction. In summary, our simulations show that both information theoretic and classifiers-based approaches can recover the type and the strength of the interaction among the salient features of an object. We are now working to apply these methods to analyze data obtained in a Bubbles-based behavioral study of rat visual object recognition.

Model-based object recognition using a large-field passive tactile sensor

The results of a model-driven touch sensor recognition experiment are reported. The touch sensor used is a large-field tactile array. Object features appropriate for touch sensor recognition are extracted from a geometric model of an object, and a dual spherical image is formed. Both geometric and dynamic features are used to identify objects and their position and orientation on the touch sensor. Experiments show that geometric features extracted from the model are effective but that dynamic features must be determined empirically. Correct object identification rates, even for very similar objects, exceed 90%, a success rate much higher than would have been expected from only two-dimensional contact patterns. The position and orientation of objects, once identified, are very reliable. The authors conclude that large-field tactile sensors could prove useful in the automatic palletizing problem when object models (from a computer-aided design system, for example) can be utilized.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Clustering by Identification with Special Application to Two-Way Tables of Counts

Abstract The formation of a partition of objects, each with an associated random measurement X, is given operational meaning and a figure of merit. The information about X, given each object, is first reduced to information about X, given the cluster in the partition to which that object belongs. The figure of merit for a partition is then the probability of a correct object identification, on the basis of a realization of X, after the information loss. An algorithm is derived for performing the calculations on two-way tables of counts.