CNN-Based Illumination Estimation with Semantic Information

Abstract

For more than a decade, both academia and industry have focused attention on the computer vision and in particular the computational color constancy (CVCC). The CVCC is used as a fundamental preprocessing task in a wide range of computer vision applications. While our human visual system (HVS) has the innate ability to perceive constant surface colors of objects under varying illumination spectra, the computer vision is facing the color constancy challenge in nature. Accordingly, this article proposes novel convolutional neural network (CNN) architecture based on the residual neural network which consists of pre-activation, atrous or dilated convolution and batch normalization. The proposed network can automatically decide what to learn from input image data and how to pool without supervision. When receiving input image data, the proposed network crops each image into image patches prior to training. Once the network begins learning, local semantic information is automatically extracted from the image patches and fed to its novel pooling layer. As a result of the semantic pooling, a weighted map or a mask is generated. Simultaneously, the extracted information is estimated and combined to form global information during training. The use of the novel pooling layer enables the proposed network to distinguish between useful data and noisy data, and thus efficiently remove noisy data during learning and evaluating. The main contribution of the proposed network is taking CVCC to higher accuracy and efficiency by adopting the novel pooling method. The experimental results demonstrate that the proposed network outperforms its conventional counterparts in estimation accuracy.

Very Deep Learning-Based Illumination Estimation Approach With Cascading Residual Network Architecture (CRNA)

“…This leads the architecture to falsely recognize small objects as noise and eliminate them. To solve the inaccuracy problem, Choi and his colleague [28], [29] set forth novel approaches by bringing the ResNet and the dilated convolution to the architecture. The two new approaches surpass their latest competitors from the estimation accuracy perspective.…”

“…[20] proposed two DCNN architectures and selected the better of the two through comparative studies. Other learning-based approaches include Bayesian learning [21], color moments [22], gamut mapping [23][24][25], spatial localization [26], [27], Choi's illuminant estimation approaches [28][29][30] and others [31], [32]. In short, the learning-based approaches have proven to outperform their statistics-based counterparts in terms of estimation accuracy throughout a lot of literature and studies.…”

Deep Learning-Based Computational Color Constancy With Convoluted Mixture of Deep Experts (CMoDE) Fusion Technique

“…In this method, a multiple illuminant detector is used to decide if it will aggregate local outputs into a single estimate. More recently, H.H.Choi et al [61] propose another color constancy approach based on the residual network architecture to overcome several problems with Alexnet-FC4 [57] such as overfitting, gradient degradation and gradient vanishing and the proposed method delivers advanced performance. Yet this method is meant to merely stack the residual blocks with skip connection.…”

Field-Applicable Pig Anomaly Detection System Using Vocalization for Embedded Board Implementations

“…The CNN algorithm is considered an important breakthrough in the image classification field, and the application of models based on it showed a remarkable increase in image recognition performance. This resulted in the CNN algorithm being employed in various fields of study [27][28][29][30]. Recently, different attempts to run such high-performance CNN models in a low-computing environment such as mobile ones have been reported [31,32].…”

“…The structure of MnasNet employed in the experiment is illustrated in Figure 3. Furthermore, the mobile bottleneck convolution (MBConv) and separable convolution (SepConv) layers used in MobileNetV2 are used here [22,28]. Each block receives an input vector of shape H × w × F (H refers to height, w to width, and F to the number of channels).…”