Length Illusion in Fractional Müller-Lyer Stimuli: An Object-Perception Approach

Perception ◽  
1993 ◽  
Vol 22 (7) ◽  
pp. 819-828 ◽  
Author(s):  
Gordon M Redding ◽  
Erik Hawley
Keyword(s):  
Artificial Intelligence ◽  
Object Recognition ◽  
Relative Position ◽  
Object Perception ◽  
Size Perception ◽  
Line Drawings ◽  
Metric Properties ◽  
Size Scaling ◽  
Central Shaft

Length judgments were compared for Müller-Lyer stimuli and figures which had line junctions at only one end of the central shaft. A length illusion occurred for fractional figures, only slightly reduced in magnitude from the usual illusion, and the largest reduction occurred for fractional figures with fork junctions. These results are consistent with an hypothesis (drawn from artificial intelligence algorithms for interpreting line drawings) that isolated line junctions are treated as boundary junctions with constrained interpretations of convex and concave edges for the shafts of arrow and fork junctions, respectively. Information about relative position of edges may be used to constrain computation of metric properties and consequential differences in size scaling would be responsible for the illusion. Illusions can arise when information well suited for one kind of task (eg object recognition) is employed in tasks for which it is not well suited (eg size perception).

scholarly journals Reports on the 2017 AAAI Spring Symposium Series

AI Magazine ◽  
2017 ◽  
Vol 38 (4) ◽  
pp. 99-106
Author(s):  
Jeannette Bohg ◽  
Xavier Boix ◽  
Nancy Chang ◽  
Elizabeth F. Churchill ◽  
Vivian Chu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Computer Science ◽  
User Experience ◽  
Object Perception ◽  
Learning Systems ◽  
Language Understanding ◽  
Social Good ◽  
Symposium Series ◽  
The Social

The Association for the Advancement of Artificial Intelligence, in cooperation with Stanford University's Department of Computer Science, presented the 2017 Spring Symposium Series, held Monday through Wednesday, March 27–29, 2017 on the campus of Stanford University. The eight symposia held were Artificial Intelligence for the Social Good (SS-17-01); Computational Construction Grammar and Natural Language Understanding (SS-17-02); Computational Context: Why It's Important, What It Means, and Can It Be Computed? (SS-17-03); Designing the User Experience of Machine Learning Systems (SS-17-04); Interactive Multisensory Object Perception for Embodied Agents (SS-17-05); Learning from Observation of Humans (SS-17-06); Science of Intelligence: Computational Principles of Natural and Artificial Intelligence (SS-17-07); and Wellbeing AI: From Machine Learning to Subjectivity Oriented Computing (SS-17-08). This report, compiled from organizers of the symposia, summarizes the research that took place.

Does context or color improve object recognition in patients with low vision?

2008 ◽  
Vol 25 (5-6) ◽  
pp. 685-691 ◽  
Author(s):  
MURIEL BOUCART ◽  
PASCAL DESPRETZ ◽  
KATRINE HLADIUK ◽  
THOMAS DESMETTRE
Keyword(s):  
Image Segmentation ◽  
Object Recognition ◽  
Low Vision ◽  
Object Perception ◽  
Age Related Macular Degeneration ◽  
Natural Scenes ◽  
Gray Level ◽  
Spatial Properties ◽  
Age Related ◽  
Complex Stimuli

AbstractMost studies on people with age-related macular degeneration (AMD) have been focused on investigations of low-level processes with simple stimuli like gratings, letters, and in perception of isolated faces or objects. We investigated the ability of people with low vision to analyze more complex stimuli like photographs of natural scenes. Fifteen participants with AMD and low vision (acuity on the better eye <20/200) and 11 normally sighted age-matched controls took part in the study. They were presented with photographs of either colored or achromatic gray level scenes in one condition and with photographs of natural scenes versus isolated objects extracted from these scenes in another condition. The photographs were centrally displayed for 300 ms. In both conditions, observers were instructed to press a key when they saw a predefined target (a face or an animal). The target was present in half of the trials. Color facilitated performance in people with low vision, while equivalent performance was found for colored and achromatic pictures in normally sighted participants. Isolated objects were categorized more accurately than objects in scenes in people with low vision. No difference was found for normally sighted observers. The results suggest that spatial properties that facilitate image segmentation (e.g., color and reduced crowding) help object perception in people with low vision.

Contrast Sensitivity in Human Visual Areas and Its Relationship to Object Recognition

2002 ◽  
Vol 87 (6) ◽  
pp. 3102-3116 ◽  
Author(s):  
Galia Avidan ◽  
Michal Harel ◽  
Talma Hendler ◽  
Dafna Ben-Bashat ◽  
Ehud Zohary ◽  
...  
Keyword(s):  
Object Recognition ◽  
High Sensitivity ◽  
Ventral Stream ◽  
High Order ◽  
Object Representations ◽  
Lateral Occipital Complex ◽  
Line Drawings ◽  
Visual Areas ◽  
The Face ◽  
Contrast Invariance

An important characteristic of visual perception is the fact that object recognition is largely immune to changes in viewing conditions. This invariance is obtained within a sequence of ventral stream visual areas beginning in area V1 and ending in high order occipito-temporal object areas (the lateral occipital complex, LOC). Here we studied whether this transformation could be observed in the contrast response of these areas. Subjects were presented with line drawings of common objects and faces in five different contrast levels (0, 4, 6, 10, and 100%). Our results show that indeed there was a gradual trend of increasing contrast invariance moving from area V1, which manifested high sensitivity to contrast changes, to the LOC, which showed a significantly higher degree of invariance at suprathreshold contrasts (from 10 to 100%). The trend toward increased invariance could be observed for both face and object images; however, it was more complete for the face images, while object images still manifested substantial sensitivity to contrast changes. Control experiments ruled out the involvement of attention effects or hemodynamic “ceiling” in producing the contrast invariance. The transition from V1 to LOC was gradual with areas along the ventral stream becoming increasingly contrast-invariant. These results further stress the hierarchical and gradual nature of the transition from early retinotopic areas to high order ones, in the build-up of abstract object representations.

Object Recognition May Distort Size Perception

2000 ◽  
Vol 90 (3) ◽  
pp. 803-809 ◽  
Author(s):  
Richard Wesp ◽  
Alissa Peckyno ◽  
Steven McCall ◽  
Sarah Peters
Keyword(s):  
Object Recognition ◽  
Size Perception

scholarly journals Comparison of subsurface object recognition by artificial neural networks and correlation method

2020 ◽  
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Object Recognition ◽  
Noise Immunity ◽  
Cross Correlation ◽  
Fdtd Method ◽  
Data Set ◽  
Electrodynamic Problem ◽  
Artificial Neural ◽  
Different Levels

Background: The problem of searching for subsurface objects has a particular interest for construction, archeology and humanitarian demining. Detection of underground mines with the help of remote sensing devices replaces the traditional procedure of finding explosive objects, as it excludes the presence of a human in the area of possible damage during a charge explosion. Objectives: The aim of the work is to improve the recognition of three-dimensional objects and demonstrate the benefits of using a more informative data set obtained by a special antenna system with four receiving antennas. In addition, it is necessary to compare the effectiveness of artificial intelligence and the method of cross-correlation for recognition by subsurface radar, taking into account the additive noise of different levels present in practice. Materials and methods: The electrodynamic problem was solved by the finite difference time domain (FDTD) method. An artificial neural network (ANN) is trained on ideal signals to detect the features of the field that will be found in noisy data to determine to the position of the object. Cross-correlation also involves the use of an array of ideal signals, which will be correlated with noisy real signals. Results: The optimal and effective ANN structure for work with the received signals is created. It was tested for noise immunity. The recognition problem was also solved by the classical method of cross-correlation, and the influence of noise of different levels on its responses was studied. In addition, a comparison of the efficiency of their recognition using 1 and 4 sensors was made. Conclusions: For subsurface survey problems, a deep neural networks with at least three hidden layers of neurons should be used. This is due to the complexity and multidimensionality of the processes taking place in the surveyed space. It has been shown that artificial intelligence and cross-correlation techniques perform the object recognition well, and it is difficult to identify the best among them. Both approaches showed good noise immunity. The use of a larger data set of four receivers has a positive effect on the recognition results.

scholarly journals Recycled Clothing Classification System Using Intelligent IoT and Deep Learning with AlexNet

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Sun-Kuk Noh
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Object Recognition ◽  
Environmental Pollution ◽  
Classification System ◽  
Raw Material ◽  
Raspberry Pi ◽  
Utilization Rate ◽  
Automation System ◽  
Labor Costs

Recently, Internet of Things (IoT) and artificial intelligence (AI), led by machine learning and deep learning, have emerged as key technologies of the Fourth Industrial Revolution (4IR). In particular, object recognition technology using deep learning is currently being used in various fields, and thanks to the strong performance and potential of deep learning, many research groups and Information Technology (IT) companies are currently investing heavily in deep learning. The textile industry involves a lot of human resources in all processes, such as raw material collection, dyeing, processing, and sewing, and the wastage of resources and energy and increase in environmental pollution are caused by the short-term waste of clothing produced during these processes. Environmental pollution can be reduced to a great extent through the use of recycled clothing. In Korea, the utilization rate of recycled clothing is increasing, the amount of used clothing is high with the annual consumption being at $56.2 billion, but it is not properly utilized because of the manual recycling clothing collection system. It has several problems such as a closed workplace environment, workers’ health, rising labor costs, and low processing speed that make it difficult to apply the existing clothing recognition technology, classified by deformation and overlapping of clothing shapes, when transporting recycled clothing to the conveyor belt. In this study, I propose a recycled clothing classification system with IoT and AI using object recognition technology to the problems. The IoT device consists of Raspberry pi and a camera, and AI uses the transfer-learned AlexNet to classify different types of clothing. As a result of this study, it was confirmed that the types of recycled clothing using artificial intelligence could be predicted and accurate classification work could be performed instead of the experience and know-how of working workers in the clothing classification worksite, which is a closed space. This will lead to the innovative direction of the recycling clothing classification work that was performed by people in the existing working worker. In other words, it is expected that standardization of necessary processes, utilization of artificial intelligence, application of automation system, various cost reduction, and work efficiency improvement will be achieved.

Neurological models of size scaling

2003 ◽  
Vol 26 (4) ◽  
pp. 425-425
Author(s):  
Helen E. Ross
Keyword(s):  
Perceptual Learning ◽  
Relative Size ◽  
Size Perception ◽  
Size Constancy ◽  
Size Discrimination ◽  
Size Scaling ◽  
Geometrical Illusions

Lehar argues that a simple Neuron Doctrine cannot explain perceptual phenomena such as size constancy but he fails to discuss existing, more complex neurological models. Size models that rely purely on scaling for distance are sparse, but several models are also concerned with other aspects of size perception such as geometrical illusions, relative size, adaptation, perceptual learning, and size discrimination.

Sign in / Sign up

Export Citation Format

Share Document