On Training Cascade Face Detectors
نویسندگان
چکیده
In this paper we present two improvements over Viola and Jones [1] training scheme for face detection. The first is 300-fold speed improvement over the training method presented by Viola and Jones [1] with a modest increase in execution time. The second is a principled method for determining a cascade classifier of optimal speed. We present some preliminary results of our methods.
منابع مشابه
Combination of Classifier Cascades and Training Sample Selection for Robust Face Detection
Face detection is one of the most fundamental tasks in human-computer-interaction, surveillance, and, more recently, image retrieval. Determining the location and size of faces in input images is a prerequisite for many other applications, including face recognition. In recent years several breakthroughs have been made in this field. These days, face detectors deliver high detection rates, low ...
متن کاملMultiple-Instance Pruning For Learning Efficient Cascade Detectors
Cascade detectors have been shown to operate extremely rapidly, with high accuracy, and have important applications such as face detection. Driven by this success, cascade learning has been an area of active research in recent years. Nevertheless, there are still challenging technical problems during the training process of cascade detectors. In particular, determining the optimal target detect...
متن کاملDOOMRED: A New Optimization Technique for Boosted Cascade Detectors on Enforced Training Set
We propose a new method to optimize the completely-trained boosted cascade detector on an enforced training set. Recently, due to the accuracy and real-time characteristics of boosted cascade detectors like the Adaboost, a lot of variant algorithms have been proposed to enhance the performance given a fixed number of training data. And, most of algorithms assume that a given training set well e...
متن کاملA Novel Bootstrapping Method for Positive Datasets in Cascades of Boosted Ensembles
We present a novel method for efficiently training a face detector using large positive datasets in a cascade of boosted ensembles. We extend the successful Viola-Jones [1] framework which achieved low false acceptance rates through bootstrapping negative samples with the capability to also bootstrap large positive datasets thereby capturing more in-class variation of the target object. We achi...
متن کاملTowards Optimal Training of Cascaded Detectors
Cascades of boosted ensembles have become popular in the object detection community following their highly successful introduction in the face detector of Viola and Jones [1]. In this paper, we explore several aspects of this architecture that have not yet received adequate attention: decision points of cascade stages, faster ensemble learning, and stronger weak hypotheses. We present a novel s...
متن کامل