Multi-task convolutional neural network system for license plate recognition

Kim, Hong-Hyun; Park, Je-Kang; Oh, Joo-Hee; Kang, Dong-Joong

doi:10.1007/s12555-016-0332-z

Cited by 41 publications

(19 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The convolutional neural network (CNN) was utilized to conduct the classification of image biomarkers. CNN is highly capable of learning appropriate features automatically from the input data by optimizing the weight parameters in individual layer by using forward and backward propagation to minimize classification errors (Ding et al, 2017; Hamadache and Lee, 2017; Kim et al, 2017; Moon et al, 2018; Trakoolwilaiwan et al, 2019). The networks in this paper consist of four layers, including two convolutional layers and two fully connected layers.…”

Section: Methodsmentioning

confidence: 99%

Evaluation of Neural Degeneration Biomarkers in the Prefrontal Cortex for Early Identification of Patients With Mild Cognitive Impairment: An fNIRS Study

Yang

Hong

Kim

2019

Front. Hum. Neurosci.

108

View full text Add to dashboard Cite

Mild cognitive impairment (MCI), a condition characterizing poor cognition, is associated with aging and depicts early symptoms of severe cognitive impairment, known as Alzheimer’s disease (AD). Meanwhile, early detection of MCI can prevent progression to AD. A great deal of research has been performed in the past decade on MCI detection. However, availability of biomarkers for MCI detection requires greater attention. In our study, we evaluated putative and reliable biomarkers for diagnosing MCI by performing different mental tasks (i.e., N-back task, Stroop task, and verbal fluency task) using functional near-infrared spectroscopy (fNIRS) signals on a group of 15 MCI patients and 9 healthy control (HC). The 15 digital biomarkers (i.e., five means, seven slopes, peak, skewness, and kurtosis) and two image biomarkers (t-map, correlation map) in the prefrontal cortex (PFC) (i.e., left PFC, middle PFC, and right PFC) between the MCI and HC groups were investigated by the statistical analysis, linear discriminant analysis (LDA), and convolutional neural network (CNN) individually. The results reveal that the statistical analysis using digital biomarkers (with a p-value < 0.05) could not distinguish the MCI patients from the HC over 60% accuracy. Therefore, the current statistical analysis needs to be improved to be used for diagnosing the MCI patients. The best accuracy with LDA was 76.67% with the N-back and Stroop tasks. However, the CNN classification results trained by image biomarkers showed a high accuracy. In particular, the CNN results trained via t-maps revealed the best accuracy (90.62%) with the N-back task, whereas the CNN result trained by the correlation maps was 85.58% with the N-back task. Also, the results illustrated that investigating the sub-regions (i.e., right, middle, left) of the PFC for detecting MCI would be better than examining the whole PFC. The t-map (or/and the correlation map) is conclusively recommended as an image biomarker for early detection of AD. The combination of CNN and image biomarkers can provide a reliable clinical tool for diagnosing MCI patients.

show abstract

Section: Methodsmentioning

confidence: 99%

Evaluation of Neural Degeneration Biomarkers in the Prefrontal Cortex for Early Identification of Patients With Mild Cognitive Impairment: An fNIRS Study

Yang

Hong

Kim

2019

Front. Hum. Neurosci.

108

View full text Add to dashboard Cite

show abstract

“… where z ∈ R n , z ′ is the rescaled value between 0 and 1, min z is the smallest value, and max z is the largest value. For efficient classifications, several classifiers have been discussed in the literature [42–48]. Here, we used an LDA classifier to verify the HbO signals.…”

Section: Methodsmentioning

confidence: 99%

An fNIRS-based investigation of visual merchandising displays for fashion stores

2018

View full text Add to dashboard Cite

This paper investigates a brain-based approach for visual merchandising display (VMD) in fashion stores. In marketing, VMD has become a research topic of interest. However, VMD research using brain activation information is rare. We examine the hemodynamic responses (HRs) in the prefrontal cortex (PFC) using functional near-infrared spectroscopy (fNIRS) while positive/negative displays of four stores (menswear, womenswear, underwear, and sportswear) are shown to 20 subjects. As features for classifying the HRs, the mean, variance, peak, skewness, kurtosis, t-value, and slope of the signals for a 20-sec time window for the activated channels are analyzed. Linear discriminant analysis is used for classifying two-class (positive and negative displays) and four-class (four fashion stores) models. PFC brain activation maps based on t-values depicting the data from the 16 channels are provided. In the two-class classification, the underwear store had the highest average classification result of 67.04%, whereas the menswear store had the lowest value of 64.15%. Men’s classification accuracy for the underwear stores with positive and negative displays was 71.38%, whereas the highest classification accuracy obtained by women for womenswear stores was 73%. The average accuracy over the 20 subjects for positive displays was 50.68%, while that of negative displays was 51.07%. Therefore, these findings suggest that human brain activation is involved in the evaluation of the fashion store displays. It is concluded that fNIRS can be used as a brain-based tool in the evaluation of fashion stores in a daily life environment.

show abstract

“…Owing to the limitation of structure, DNN with eight branches of fully connected layers that are built in [8] can recognise license plates with no more than eight characters. In addition, Kim et al [42] proposed a multi-task DNN to recognise the license plate. Intel proposed an efficient neural network called LPRNet [43], which could handle the ALPR problem in <3 ms.…”

Section: End-to-end Alprmentioning

confidence: 99%