Object Recognition Using Glove Tactile Sensor

Pohtongkam, Somchai; Srinonchat, Jakkree

doi:10.1109/ieecon53204.2022.9741672

Cited by 5 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first method uses a BoW Model [34] with a workflow, as shown in Figure 12 [40], [45] Clustering for BoW was applied to image recognition and tactile recognition [34], [35], [39]. Use the K-Mean method as an unsupervised learning method for grouping data.…”

Section: F Bag Of Word Methodsmentioning

confidence: 99%

“…One of the essential developments of the humanoid robot hand is tactile object recognition. It has been reported in various research studies [6], [7], [16], [19], [21], [22], [23], [24], [25], [29], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45]. The important element for processing is the installation data of the tactile sensor array, so-called tactile image recognition, as summarized in Table 2.…”

Section: B Object Recognition Based On Tactile Imagementioning

confidence: 99%

“…The tactile sensor used in this research was developed from a square electrode piezoresistive sensor [6], [45] by dividing the number of sensors into 15 parts according to the characteristics of the palm [8], [10]. The sensor is designed to be a Full Hand Tactile Sensor, as shown in Figure 1.…”

Section: B Full Hand Tactile Sensor and Robot Handmentioning

confidence: 99%

See 2 more Smart Citations

Object Recognition for Humanoid Robots Using Full Hand Tactile Sensor

Pohtongkam

Srinonchat

2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

With the development of human-like robotic technologies, robots have been advanced to sense and recognize objects, which is one branch of artificial intelligence to mimic human reactions. Although high-performance computer technologies are used, the ability of object recognition by touch is still low due to the lack of proper sensors. Therefore, this research studied the object learning and recognition system through robot touches by developing an artificial sensory system acting as an electronic skin with tactile sensors. The Tactile Sensor is developed in this research, consisting of 15 Tactile Sensor Arrays and the palm's touchpoints. Furthermore, recognition analysis was developed on Bag of Word (BoW) and Convolution Neural Network (CNN) algorithms. With the BoW technique, using Support Vector Machine (SVM) as a classifier with Moment Analysis Descriptor (MA) provided the highest accuracy, showing more than 80.15% accuracy from five grasping of an object. With the CNN approach, InceptionNetV3 provided the highest accuracy of 98.28% from only one capture of an object.INDEX TERMS Bag of feature, bag of word, CNN, robot hand, tactile object recognition, tactile sensor, transfer learning.

show abstract