Street view image classification based on convolutional neural network

  title={Street view image classification based on convolutional neural network},
  author={Q. Wang and Cailan Zhou and N. Xu},
  journal={2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)},
  • Q. Wang, Cailan Zhou, N. Xu
  • Published 2017
  • Computer Science
  • 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)
This paper utilizes the deep learning algorithm to classify the Street View images. We did some research to find the appropriate convolutional neural network model that suits the classification of the street view images. We firstly collected our own dataset. Based on the convolutional neural network model AlexNet and according to the characteristics the dataset mentioned above to adjust the model structure and training methods. Experiments utilize max-pooling as sampling model, set the number… Expand
A Visual Sensing Concept for Robustly Classifying House Types through a Convolutional Neural Network Architecture Involving a Multi-Channel Features Extraction
This paper develops and validate a comprehensive visual sensing concept for robustly classifying house types and reaches classification performance figures which are at least 8% higher than those reached by the previous state-of-the-art methods involved in the conducted comprehensive benchmarking. Expand
Palm Oil Fresh Fruit Bunch Ripeness Grading Recognition Using Convolutional Neural Network
Results indicate that with a small number of sample data, pre-trained CNN model, AlexNet, outperforms CNN and the hand-crafted feature and classifier approach for palm oil Fresh Fruit Bunch ripeness grading recognition. Expand
Urban land-use analysis using proximate sensing imagery: a survey
The propagation of online geographic information-sharing platforms and mobile apps in urban regions are complicated functional systems that are closely associated with and reshaped by human activities. Expand


ImageNet classification with deep convolutional neural networks
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks
This paper employs the DistBelief implementation of deep neural networks in order to train large, distributed neural networks on high quality images and finds that the performance of this approach increases with the depth of the convolutional network. Expand
Going deeper with convolutions
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual RecognitionExpand
Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree
The proposed pooling operations provide a boost in invariance properties relative to conventional pooling and set the state of the art on several widely adopted benchmark datasets; they are also easy to implement, and can be applied within various deep neural network architectures. Expand
Fractional Max-Pooling
The form of fractional max-pooling formulated is found to reduce overfitting on a variety of datasets: for instance, it improves on the state of the art for CIFAR-100 without even using dropout. Expand
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
The "exponential linear unit" (ELU) which speeds up learning in deep neural networks and leads to higher classification accuracies and significantly better generalization performance than ReLUs and LReLUs on networks with more than 5 layers. Expand
Stacked What-Where Auto-encoders
We present a novel architecture, the "stacked what-where auto-encoders" (SWWAE), which integrates discriminative and generative pathways and provides a unified approach to supervised, semi-supervisedExpand
Train faster, generalize better: Stability of stochastic gradient descent
We show that parametric models trained by a stochastic gradient method (SGM) with few iterations have vanishing generalization error. We prove our results by arguing that SGM is algorithmicallyExpand
Fast and accurate deep network learning by exponential linear units (elus)[J
  • arXiv preprint arXiv:1511.07289,
  • 2015