Early feature stream integration versus decision level combination in a multiple classifier system for text line recognition

Bertolami, Roman; Bunke, Horst

doi:10.1109/icpr.2006.466

Cited by 10 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The decision-level approach has the benefit of being very easy to implement when the independent systems are already available in the literature. The feature-level approach has the drawback of being often difficult to implement, as different information queues are often different in nature and are thus difficult to incorporate in one uniform processing scheme, but, when successfully realized, produces systems that are able to achieve considerably better performances [8].…”

Section: Methodology Outlinementioning

confidence: 99%

Multimodal user’s affective state analysis in naturalistic interaction

Karpouzis

Wallace

Kessous

et al. 2009

J Multimodal User Interfaces

View full text Add to dashboard Cite

Affective and human-centered computing have attracted an abundance of attention during the past years, mainly due to the abundance of environments and applications able to exploit and adapt to multimodal input from the users. The combination of facial expressions with prosody information allows us to capture the users' emotional state in an unintrusive manner, relying on the best performing modality in cases where one modality suffers from noise or bad sensing conditions. In this paper, we describe a multicue, dynamic approach to detect emotion in naturalistic video sequences, where input is taken from nearly real world situations, contrary to controlled recording conditions of audiovisual material. Recognition is performed via a recurrent neural network, whose short term memory and approximation capabilities cater for modeling dynamic events in facial and prosodic expressivity. This approach also differs from existing work in that it models user expressivity using a dimensional representation, instead of detecting discrete 'universal emotions', which are scarce in everyday human-G. Caridakis ( ) · K. Karpouzis Image, Video and machine interaction. The algorithm is deployed on an audiovisual database which was recorded simulating humanhuman discourse and, therefore, contains less extreme expressivity and subtle variations of a number of emotion labels. Results show that in turns lasting more than a few frames, recognition rates rise to 98%.

show abstract

Section: Methodology Outlinementioning

confidence: 99%

Multimodal user’s affective state analysis in naturalistic interaction

Karpouzis

Wallace

Kessous

et al. 2009

J Multimodal User Interfaces

View full text Add to dashboard Cite

show abstract

“…( Bertolami and Bunke, 2006) compare these two combination methods in the case of offline handwritten text line recognition and shows that both combination methods improve recognition performances compared to any recognisers built from the individual feature streams. Furthermore, in their case, the early integration approach outperforms the decision level combination.…”

Section: Figure 1 : Feature Combination Approachmentioning

confidence: 99%

Off-line handwritten word recognition using multi-stream hidden Markov models

Kessentini

Paquet

Hamadou

2010

Pattern Recognition Letters

View full text Add to dashboard Cite

To cite this version:Yousri Kessentini, Thierry Paquet, Abdelmajid Benhamadou. Off-line handwritten word recognition using multi-stream hidden Markov models. Pattern Recognition Letters, Elsevier, 2010, 31 (1) AbstractIn this paper, we present a multi-stream approach for off-line handwritten word recognition. Using 2-stream approach, the best recognition performance is 79.8%, in the case of the Arabic script, on a 2100-word lexicon consisting of 946 Tunisian town/village names. In the case of the Latin script, the proposed approach achieves a recognition rate of 89.8 % using a lexicon of 196 words.2 KeywordsOff-Line handwriting recognition, Hidden Markov Models, Latin script, Arabic script, multistream, information combination.

show abstract

“…To avoid simply using the voting procedure as ROVER, Bertolami et al 5 described a system ensemble method through statistical decision. In their other work, 6 Bertolami et al proposed a method to integrate geometric and pixel-based features into OCR combination for text line recognition.…”

Section: Introductionmentioning

confidence: 98%

Boost OCR accuracy using iVector based system combination approach

2015

View full text Add to dashboard Cite

Optical character recognition (OCR) is a challenging task because most existing preprocessing approaches are sensitive to writing style, writing material, noises and image resolution. Thus, a single recognition system cannot address all factors of real document images. In this paper, we describe an approach to combine diverse recognition systems by using iVector based features, which is a newly developed method in the field of speaker verification. Prior to system combination, document images are preprocessed and text line images are extracted with different approaches for each system, where iVector is transformed from a high-dimensional supervector of each text line and is used to predict the accuracy of OCR. We merge hypotheses from multiple recognition systems according to the overlap ratio and the predicted OCR score of text line images. We present evaluation results on an Arabic document database where the proposed method is compared against the single best OCR system using word error rate (WER) metric.

show abstract

Early feature stream integration versus decision level combination in a multiple classifier system for text line recognition

Cited by 10 publications

References 18 publications

Multimodal user’s affective state analysis in naturalistic interaction

Multimodal user’s affective state analysis in naturalistic interaction

Off-line handwritten word recognition using multi-stream hidden Markov models

Boost OCR accuracy using iVector based system combination approach

Contact Info

Product

Resources

About