Multi-column Deep Neural Networks for Image Classification Supplementary Online Material
نویسندگان
چکیده
The confusion matrix of the 62 characters task (Fig. 1) shows that most of the errors are due to confusions between digits and letters and between lower-and upper-case letters. Figure 1. Confusion matrix of the NIST SD 19 MCDNN trained on the 62-class task: correct labels on vertical axis; detected labels on horizontal axis. Square areas are proportional to error numbers, shown as relative percentages of the total error number. For convenience, class labels are written beneath the errors. Errors below 1% of the total error number are not detailed. Not very surprisingly, the confusion matrix for the digit task (Fig. 2) shows that confusions between fours and nines are the most common error source.
منابع مشابه
Porosity classification from thin sections using image analysis and neural networks including shallow and deep learning in Jahrum formation
The porosity within a reservoir rock is a basic parameter for the reservoir characterization. The present paper introduces two intelligent models for identification of the porosity types using image analysis. For this aim, firstly, thirteen geometrical parameters of pores of each image were extracted using the image analysis techniques. The extracted features and their corresponding pore types ...
متن کاملIdentification of Houseplants Using Neuro-vision Based Multi-stage Classification System
In this paper, we present a machine vision system that was developed on the basis of neural networks to identify twelve houseplants. Image processing system was used to extract 41 features of color, texture and shape from the images taken from front and back of the leaves. The features were fed into the neural network system as the recognition criteria and inputs. Multilayer perceptron (MLP) ne...
متن کاملMulti-column deep neural network for traffic sign classification
We describe the approach that won the final phase of the German traffic sign recognition benchmark. Our method is the only one that achieved a better-than-human recognition rate of 99.46%. We use a fast, fully parameterizable GPU implementation of a Deep Neural Network (DNN) that does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. Combi...
متن کاملMulti-view, Multi-label Learning with Deep Neural Networks
Deep learning is a popular technique in modern online and offline services. Deep neural network based learning systems have made groundbreaking progress in model size, training and inference speed, and expressive power in recent years, but to tailor the model to specific problems and exploit data and problem structures is still an ongoing research topic. We look into two types of deep ‘‘multi-’...
متن کاملRejection of the Feed-Flow Disturbances in a Multi-Component Distillation Column Using a Multiple Neural Network Model-Predictive Controller
This article deals with the issues associated with developing a new design methodology for the nonlinear model-predictive control (MPC) of a chemical plant. A combination of multiple neural networks is selected and used to model a nonlinear multi-input multi-output (MIMO) process with time delays. An optimization procedure for a neural MPC algorithm based on this model is then developed. T...
متن کامل