We present a robust connected-component (CC) based method for automatic detection and segmentation of text in real-scene images. This technique can be applied in robot vision, sign recognition, meeting processing and video indexing. First, a non-linear Niblack method (NLNiblack) is proposed to decompose the image into candidate CCs. Then, we feed all these CCs into a cascade of classifiers trained by Adaboost algorithm. Each classifier in the cascade responds to one feature of the CC. We propose 12 novel features which are insensitive to noise, scale, text orientation and text language. The classifier cascade allows non-text CCs of the image to be quickly discarded while spending more computation on promising text-like CCs. The CCs passing through the cascade are considered as text components and are used to form the segmentation result. We have built a prototype system and the experimental results prove the effectiveness and efficiency of the proposed method.