Multiple eliminations (de-multiple) are one of seismic processing steps to remove their effects and delineate the correct primary refractors. Using normal move out to flatten primaries is the way to eliminate multiples through transforming these data to frequency-wavenumber domain. The flatten primaries are aligned with zero axis of the frequency-wavenumber domain and any other reflection types (multiples and random noise) are distributed elsewhere. Dip-filter is applied to pass the aligned data and reject others will separate primaries from multiple after transforming the data back from frequency-wavenumber domain to time-distance domain. For that, a suggested name for this technique as normal move out- frequency-wavenumber domain method for multiple eliminations. The method is tested on a fake reflection event to authorize their validity, and applied to a real field X-profile 2D seismic data from southern Iraq. The results ensure the possibility of internal multiple types existing in the deep reflection data in Iraq and have to remove. So that the interpretation for the true reflectors be valid. The final processed stacked seismic data using normal move out- frequency-wavenumber domain technique shows good, clear, and sharp reflectors in comparison with the conventional normal move out stack data. Open-source Madagascar reproducible package is used for processing all steps of this study and the package is very efficient, accurate, and easy to implement normal move out, frequency-wavenumber domain, Dip-filter programs. The aim of the current study is to separate internal multiples and noise from the real 2D seismic data.