Segmentation of moving images by the human visual system

Chantelau, Klaus

doi:10.1007/s004220050370

Cited by 6 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This implementation mirrors processes related to language acquisition, partly based on the segmentation of the speech stream into word units. The same applies for studies on human image-sequence segmentation (Chantelau, 1997). For a given piece of music, however, there is nothing that corresponds to a predefined set of sequentially presented tones or sets of tones ("words") out of which the piece of music is built.…”

Section: Differencesmentioning

confidence: 99%

A Recurrent Connectionist Model of Melody Perception: An Exploration Using TRACX2

Defays¹,

French

Tillmann

2023

Cognitive Science

View full text Add to dashboard Cite

Are similar, or even identical, mechanisms used in the computational modeling of speech segmentation, serial image processing, and music processing? We address this question by exploring how TRACX2, a recognition‐based, recursive connectionist autoencoder model of chunking and sequence segmentation, which has successfully simulated speech and serial‐image processing, might be applied to elementary melody perception. The model, a three‐layer autoencoder that recognizes “chunks” of short sequences of intervals that have been frequently encountered on input, is trained on the tone intervals of melodically simple French children's songs. It dynamically incorporates the internal representations of these chunks into new input. Its internal representations cluster in a manner that is consistent with “human‐recognizable” melodic categories. TRACX2 is sensitive to both contour and proximity information in the musical chunks that it encounters in its input. It shows the “end‐of‐word” superiority effect demonstrated by Saffran et al. (1999) for short musical phrases. The overall findings suggest that the recursive autoassociative chunking mechanism, as implemented in TRACX2, may be a general segmentation and chunking mechanism, underlying not only word‐ and image‐chunking, but also elementary melody processing.

show abstract

Section: Differencesmentioning

confidence: 99%

A Recurrent Connectionist Model of Melody Perception: An Exploration Using TRACX2

Defays¹,

French

Tillmann

2023

Cognitive Science

View full text Add to dashboard Cite

show abstract

“…Different visual information causes different stimulation on the visual light-sensitive cells, with the most significant information gaining the attention of the human eyes. HVM has been successfully applied in the field of image processing [16,17,18,19,20], which can quickly localize the ROI, and automatically discard the unimportant parts. Thus, this saves a lot of image post-processing time.…”

Section: Model Architecturementioning

confidence: 99%

An Automatic Localization Algorithm for Ultrasound Breast Tumors Based on Human Visual Mechanism

Xie

Chen

Lin

2017

Sensors

View full text Add to dashboard Cite

Human visual mechanisms (HVMs) can quickly localize the most salient object in natural images, but it is ineffective at localizing tumors in ultrasound breast images. In this paper, we research the characteristics of tumors, develop a classic HVM and propose a novel auto-localization method. Comparing to surrounding areas, tumors have higher global and local contrast. In this method, intensity, blackness ratio and superpixel contrast features are combined to compute a saliency map, in which a Winner Take All algorithm is used to localize the most salient region, which is represented by a circle. The results show that the proposed method can successfully avoid the interference caused by background areas of low echo and high intensity. The method has been tested on 400 ultrasound breast images, among which 376 images succeed in localization. This means this method has a high accuracy of 94.00%, indicating its good performance in real-life applications.

show abstract

“…Methods for sensory measurement have been widely and actively studied both in Japan and elsewhere. References [1], [2], [3] and [9] are typical examples. However, the vague and objective nature of human senses has so far made it impossible to systematize them in a scientific fashion.…”

Section: Introductionmentioning

confidence: 99%

Manipulator operation by using brain-wave signals

Shiraishi

Sumiya

2005

2005 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

When we look at a comfortable scene or feel relaxed, our brain waves generally exhibit wave signals in the frequency band of approximately 8 to 13 Hz. These waves particularly exhibit a 1/f fluctuation in which the corresponding power is inversely proportional to frequency f. 1/f -wave signals obtained from test subjects listening to relaxing music was inputted to a robot manipulator. To evaluate the resulting motions, test subjects were asked to complete questionnaires while they watched two types of manipulator motions: a 1/f motion and a white-noise-like motion. The results indicated that 90% of the subjects felt comfortable while watching the 1/f manipulator motions.

show abstract

Segmentation of moving images by the human visual system

Cited by 6 publications

References 16 publications

A Recurrent Connectionist Model of Melody Perception: An Exploration Using TRACX2

A Recurrent Connectionist Model of Melody Perception: An Exploration Using TRACX2

An Automatic Localization Algorithm for Ultrasound Breast Tumors Based on Human Visual Mechanism

Manipulator operation by using brain-wave signals

Contact Info

Product

Resources

About