Objects and scenes classification with selective use of central and peripheral image content

Abstract

The human visual recognition system is more efficient than any current robotic vision setting. One reason for this superiority is that humans utilize different fields of vision, depending on the recognition task. For instance, experiments on human subjects show that the peripheral vision is more useful than the central vision in recognizing scenes. We tested our recently-developed model, that is, the elastic net-regularized hierarchical MAX (En-HMAX), in recognizing objects and scenes. In various experimental conditions, images were occluded with windows and scotomas of varying sizes. With this model, classification accuracies of up to 90% for objects and scenes were possible. Modelling human experiments, window and scotoma analysis with the En-HMAX model revealed that object and scene recognition are sensitive to the availability of data in the centre and the periphery of the images, respectively. Similarly, results of deep learning models have shown that the classification accuracy diminishes dramatically in the absence of the peripheral vision. These differences led us to further analyse the performance of the En-HMAX model with the parafoveal versus peripheral areas of vision, in a second study. Results of the second study show that approximately 50% of the visual field would be sufficient to achieve 96% accuracy in the classification of unseen images. The En-HMAX model adopts a relative order of importance, similar to the human visual system, depending on the image category. We showed that utilizing the relevant regions of vision can significantly reduce the image processing time and size.

Automated recognition of postures and drinking behaviour for the detection of compromised health in pigs

“…Video surveillance is a suitable technology to identify drinking 8 and feeding 9 behaviour in pigs, due to its low cost and the simplicity of its implementation, and a good alternative to Radio-frequency identification systems installed around drinking systems and feeding stations 10 . The crucial element of this approach is how to extract formative features from the images 11 – 13 , i.e. that can provide appropriate information regarding the health of the pigs in a manner that has relevance to the pig keeper.…”

An Electro-Oculogram Based Vision System for Grasp Assistive Devices—A Proof of Concept Study

“…Therefore, no additional training is required for the users. (4) Adopt a simple image processing algorithm to avoid high processing unit: Existing vision systems are using advance machine learning mechanism [ 12 , 16 , 20 , 21 , 24 ] which require high processor and large storage capacity. In the developed vision system, a simple colour based segmentation technique was applied and after that only the object boundary was used for object width and orientation estimation.…”

“…Along with the control approach, the use of computer vision systems entails a real-time implementation of sophisticated algorithms typically [ 16 , 20 , 21 ]. With the advent of deep learning methods, grasp research has considerably advanced.…”

A Comprehensive Review of AI Techniques for Addressing Algorithmic Bias in Job Hiring

“…This offsets the weaknesses resulting from a single inaccurate data source. However, AI faces a serious issue when there is a defined target variable that the model is expected to predict [88]. For instance, an organization may use non-protected aspects like sales numbers to make hiring decisions.…”