Image steganography is a technique to hide secret information in an image without leaving any apparent evidence of image alteration. Hiding capacity, perceptual transparency, robustness, and resistance against attack must be considered as characteristics of the image steganography algorithms. In this study, Improved Chaos Based Bit Embedding has been proposed as a new steganography algorithm. It is based on two basic principles. One of them is determining the bits in which the secret data will be embedded by logistic map and the other one is embedding the secret data into only one of the three color channels that is chosen randomly. It distorts the other remaining channels so that it is harder to obtain the text within the image by an unwanted person. The proposed algorithm has been tested on 10 sample images along with the four basic steganography algorithms: Least Significant Bit Embedding, Pseudo Random Least Significant Bit Embedding, EzStego, and F5. It has been seen that generating unpredictable indexes by the chaotic random number generators, and embedding the secret data into only one of the three channels (distorting remaining channels) increased resistance against attacks. Perceptual transparencies and capacity ratio of the proposed algorithm are compatible with the other four algorithms.