Enhancing human sight perceptions to optimize machine vision: Untangling object recognition using deep learning techniques
The goal of machine vision is to develop human-like visual abilities; however, it is unclear whether understanding human vision will advance machines. Here, it exemplifies two key conceptual advancements: It first shows that the majority of computer vision models consistently differ from the way tha...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-08-01
|
| Series: | Measurement: Sensors |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2665917423001897 |
| _version_ | 1797780689502863360 |
|---|---|
| author | Sharika Krishnaveni S Kavitha Subramani Sharmila L Sathiya V Maheswari M Priyaadarshan B |
| author_facet | Sharika Krishnaveni S Kavitha Subramani Sharmila L Sathiya V Maheswari M Priyaadarshan B |
| author_sort | Sharika Krishnaveni S |
| collection | DOAJ |
| description | The goal of machine vision is to develop human-like visual abilities; however, it is unclear whether understanding human vision will advance machines. Here, it exemplifies two key conceptual advancements: It first shows that the majority of computer vision models consistently differ from the way that individuals perceive objects. To do this, a significant dataset of human perceptions of the separations of isolated things was acquired, and it was then examined to see if a well-known machine vision algorithm can predict these perceptions. The best algorithms can account for the majority of the volatility in the intuitive data, but every algorithm we verified repeatedly misjudged several different object types. Second, it shows that removing these systemic biases can considerably increase classification accuracy. For instance, machine techniques overestimated detachments between symmetric objects in comparison to human vision. These results illustration that methodical differences between human and machine vision can be identified and improved.In order to improve the machine vision, employing a deep learning algorithm Visual Geometry Group (VGG 16) with planar reflection symmetry (PRS-Net) technique. VGG 16 is a convolutional neural network with 16 deep layers. VGG pre-trained architecture can point out visual features present in the image. The planar reflection symmetry concept is appended with VGG to create a hybrid environment that can improve machine vision significantly by 90%. |
| first_indexed | 2024-03-12T23:47:32Z |
| format | Article |
| id | doaj.art-925896df8b5449abbd17cb00904794d1 |
| institution | Directory Open Access Journal |
| issn | 2665-9174 |
| language | English |
| last_indexed | 2024-03-12T23:47:32Z |
| publishDate | 2023-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Measurement: Sensors |
| spelling | doaj.art-925896df8b5449abbd17cb00904794d12023-07-14T04:28:30ZengElsevierMeasurement: Sensors2665-91742023-08-0128100853Enhancing human sight perceptions to optimize machine vision: Untangling object recognition using deep learning techniquesSharika Krishnaveni S0Kavitha Subramani1Sharmila L2Sathiya V3Maheswari M4Priyaadarshan B5Department of Computer Science and Engineering, Panimalar Engineering College, Chennai, India; Corresponding author.Department of Computer Science and Engineering, Panimalar Engineering College, Chennai, IndiaDepartment of Computer Science and Engineering, Agni College of Technology, Chennai, IndiaDepartment of Computer Science and Engineering, Panimalar Engineering College, Chennai, IndiaDepartment of Computer Science and Engineering, Panimalar Engineering College, Chennai, IndiaDepartment of Information Technology, Panimalar Institute of Technology, Chennai, IndiaThe goal of machine vision is to develop human-like visual abilities; however, it is unclear whether understanding human vision will advance machines. Here, it exemplifies two key conceptual advancements: It first shows that the majority of computer vision models consistently differ from the way that individuals perceive objects. To do this, a significant dataset of human perceptions of the separations of isolated things was acquired, and it was then examined to see if a well-known machine vision algorithm can predict these perceptions. The best algorithms can account for the majority of the volatility in the intuitive data, but every algorithm we verified repeatedly misjudged several different object types. Second, it shows that removing these systemic biases can considerably increase classification accuracy. For instance, machine techniques overestimated detachments between symmetric objects in comparison to human vision. These results illustration that methodical differences between human and machine vision can be identified and improved.In order to improve the machine vision, employing a deep learning algorithm Visual Geometry Group (VGG 16) with planar reflection symmetry (PRS-Net) technique. VGG 16 is a convolutional neural network with 16 deep layers. VGG pre-trained architecture can point out visual features present in the image. The planar reflection symmetry concept is appended with VGG to create a hybrid environment that can improve machine vision significantly by 90%.http://www.sciencedirect.com/science/article/pii/S2665917423001897Machine visionPerceptionsComputational modelsConvolutional neural networksDeep learning |
| spellingShingle | Sharika Krishnaveni S Kavitha Subramani Sharmila L Sathiya V Maheswari M Priyaadarshan B Enhancing human sight perceptions to optimize machine vision: Untangling object recognition using deep learning techniques Measurement: Sensors Machine vision Perceptions Computational models Convolutional neural networks Deep learning |
| title | Enhancing human sight perceptions to optimize machine vision: Untangling object recognition using deep learning techniques |
| title_full | Enhancing human sight perceptions to optimize machine vision: Untangling object recognition using deep learning techniques |
| title_fullStr | Enhancing human sight perceptions to optimize machine vision: Untangling object recognition using deep learning techniques |
| title_full_unstemmed | Enhancing human sight perceptions to optimize machine vision: Untangling object recognition using deep learning techniques |
| title_short | Enhancing human sight perceptions to optimize machine vision: Untangling object recognition using deep learning techniques |
| title_sort | enhancing human sight perceptions to optimize machine vision untangling object recognition using deep learning techniques |
| topic | Machine vision Perceptions Computational models Convolutional neural networks Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S2665917423001897 |
| work_keys_str_mv | AT sharikakrishnavenis enhancinghumansightperceptionstooptimizemachinevisionuntanglingobjectrecognitionusingdeeplearningtechniques AT kavithasubramani enhancinghumansightperceptionstooptimizemachinevisionuntanglingobjectrecognitionusingdeeplearningtechniques AT sharmilal enhancinghumansightperceptionstooptimizemachinevisionuntanglingobjectrecognitionusingdeeplearningtechniques AT sathiyav enhancinghumansightperceptionstooptimizemachinevisionuntanglingobjectrecognitionusingdeeplearningtechniques AT maheswarim enhancinghumansightperceptionstooptimizemachinevisionuntanglingobjectrecognitionusingdeeplearningtechniques AT priyaadarshanb enhancinghumansightperceptionstooptimizemachinevisionuntanglingobjectrecognitionusingdeeplearningtechniques |